109 accepted papers
Taking advantage of large-scale data and pretrained language models, Video Large Language Models (Video-LLMs) have shown strong capabilities in answering video questions. However, most existing efforts focus on improving performance, with limited attention to understanding their internal mechanisms.
Chain-of-Thought (CoT) prompting has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing implementations, such as in-context learning and fine-tuning, remain costly and inefficient. To improve CoT reasoning at a lower cost, and in…
Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models. Block diffusion improves inference efficiency via KV caching and block-wise causal inference and has been widely adopted in diffusion language models and video generat…
Diffusion models have shown remarkable performance in image synthesis by progressively estimating a smooth transition from a Gaussian distribution of noise to a real image. Unfortunately, their practical deployment is limited by slow inference speed, high memory usage, and the computational demands…
Optimizing the similarity between parametric shapes is crucial for numerous computer vision tasks, where Intersection over Union (IoU) stands as the canonical measure. However, existing optimization methods exhibit significant shortcomings: regression-based losses like L1/L2 lack correlation with Io
We present MotionCrafter, a framework that leverages video generators to jointly reconstruct 4D geometry and estimate dense motion from a monocular video. The key idea is a joint representation of dense 3D point maps and 3D scene flows in a shared coordinate system, together with a 4D VAE tailored t
Training a unified model integrating video-to-audio (V2A), text-to-audio (T2A), and joint video-text-to-audio (VT2A) generation offers significant application flexibility, yet faces two unexplored foundational challenges: (1) the scarcity of high-quality audio captions with tight V-A-T alignment, le
We present Ov3R, a novel framework for open-vocabulary semantic 3D reconstruction from RGB video streams, designed to advance Spatial AI. The system features two key components: CLIP3R, a CLIP-informed 3D reconstruction module that predicts dense point maps from overlapping clips alongside object-le
3D Gaussian Splatting (3DGS) achieves impressive rendering fidelity and speed for novel view synthesis. However, its substantial data size poses a significant challenge for practical applications. While many compression techniques have been proposed, they fail to efficiently utilize existing bitstre
Panoramic video generation has attracted growing attention due to its applications in virtual reality and immersive media. However, existing methods lack explicit motion control and struggle to generate scenes with large and complex motions. We propose PanFlow a novel approach that exploits the sphe
Reinforcement learning with verifiable rewards (RLVR) can yield large reasoning gains from very few training instances, yet its strong sensitivity to which instances are used makes data selection a central bottleneck. Most existing selection pipelines rely on training-time optimization signals and/o…
Transformers have emerged as a universal backbone across 3D perception, video generation, and world models for autonomous driving and embodied AI, where understanding camera geometry is essential for grounding visual observations in three-dimensional space. However, existing camera encoding methods
This paper studies Visual Question-Visual Answering (VQ-VA): generating an image, rather than text, in response to a visual question---an ability that has recently emerged in proprietary systems such as NanoBanana and GPT-Image. To also bring this capability to open-source models, we introduce VQ-VA
Magnetic resonance imaging (MRI) is a powerful and versatile imaging technique, offering a wide spectrum of information about the anatomy by employing different acquisition modalities. However, in the clinical workflow, it is impractical to collect all relevant modalities due to the scan time and co
Large Multimodal Models (LMMs) have shown promising in-context learning (ICL) capabilities, but scaling to many-shot settings remains difficult due to limited context length and high inference cost. To address these challenges, task-vector-based methods have been explored by inserting compact repres
Most of the existing methods for video understanding primarily focus on videos only lasting tens of seconds, with limited exploration of techniques for handling long videos. The increased number of frames in long videos poses two main challenges: difficulty in locating key information and performing…
With 3D Gaussian Splatting (3DGS) advancing real-time and high-fidelity rendering for novel view synthesis, storage requirements pose challenges for their widespread adoption. Although various compression techniques have been proposed, previous art suffers from a common limitation: for any existing…
Personalizing a large-scale pretrained Text-to-Image (T2I) diffusion model is chal- lenging as it typically struggles to make an appropriate trade-off between its training data distribution and the target distribution, i.e., learning a novel concept with only a few target images to achieve personali…
With the advent of portable 360deg cameras, panorama has gained significant attention in applications like virtual reality (VR), virtual tours, robotics, and autonomous driving. As a result, wide-baseline panorama view synthesis has emerged as a vital task, where high resolution, fast inference, and…
This paper proposes a general solution to enable point cloud recognition models to handle distribution shifts at test time. Unlike prior methods, which rely heavily on training data (often inaccessible during online inference) and are limited to recognizing a fixed set of point cloud classes predefi…
Sampling from diffusion probabilistic models (DPMs) is often expensive for high-quality image generation and typically requires many steps with a large model. In this paper, we introduce sampling Trajectory Stitching (T-Stitch), a simple yet efficient technique to improve the sampling efficiency wit…
Video diffusion models (VDMs) have advanced significantly in recent years, enabling the generation of highly realistic videos and drawing the attention of the community in their potential as world simulators. However, despite their capabilities, VDMs often fail to produce physically plausible videos…
"This paper presents a novel approach for the differentiable rendering of convex polyhedra, addressing the limitations of recent methods that rely on implicit field supervision. Our technique introduces a strategy that combines non-differentiable computation of hyperplane intersection through dualit…
"Diffusion models have recently gained prominence as powerful deep generative models, demonstrating unmatched performance across various domains. However, their potential in multi-sensor fusion remains largely unexplored. In this work, we introduce “DifFUSER”, a novel approach that leverages diffusi…
Annotation ambiguity due to inherent data uncertainties such as blurred boundaries in medical scans and different observer expertise and preferences has become a major obstacle for training deep-learning based medical image segmentation models. To address it the common practice is to gather multiple…
The paradigm of pre-training and fine-tuning has laid the foundation for deploying deep learning models. However most fine-tuning methods are designed to meet a specific resource budget. Recently considering diverse deployment scenarios with various resource budgets SN-Net is introduced to quickly o…
Large Vision-Language Models (LVLMs) are capable of handling diverse data types such as imaging, text, and physiological signals, and can be applied in various fields. In the medical field, LVLMs have a high potential to offer substantial assistance for diagnosis and treatment. Before that, it is cr…
In recent research significant attention has been devoted to the open-vocabulary object detection task aiming to generalize beyond the limited number of classes labeled during training and detect objects described by arbitrary category names at inference. Compared with conventional object detection…
"3D Gaussian Splatting (3DGS) has emerged as a promising framework for novel view synthesis, boasting rapid rendering speed with high fidelity. However, the substantial Gaussians and their associated attributes necessitate effective compression techniques. Nevertheless, the sparse and unorganized na…
In recent years Neural Radiance Field (NeRF) has demonstrated remarkable capabilities in representing 3D scenes. To expedite the rendering process learnable explicit representations have been introduced for combination with implicit NeRF representation which however results in a large storage space…
Autonomous robot systems have attracted increasing research attention in recent years where environment understanding is a crucial step for robot navigation human-robot interaction and decision. Real-world robot systems usually collect visual data from multiple sensors and are required to recognize…
We introduce MVSplat360, a feed-forward approach for 360° novel view synthesis (NVS) of diverse real-world scenes, using only sparse observations. This setting is inherently ill-posed due to minimal overlap among input views and insufficient visual information provided, making it challenging for con…
"We introduce , an efficient model that, given sparse multi-view images as input, predicts clean feed-forward 3D Gaussians. To accurately localize the Gaussian centers, we build a cost volume representation via plane sweeping, where the cross-view feature similarities stored in the cost volume can p…
"Iso-surface extraction from an implicit field is a fundamental process in various applications of computer vision and graphics. When dealing with geometric shapes with complicated geometric details, many existing algorithms suffer from high computational costs and memory usage. This paper proposes…
Rendering and reconstruction are long-standing topics in computer vision and graphics. Achieving both high rendering quality and accurate geometry is a challenge. Recent advancements in 3D Gaussian Splatting (3DGS) have enabled high-fidelity novel view synthesis at real-time speeds. However, the noi…
This paper investigates the 3D domain generalization (3DDG) ability of large 3D models based on prevalent prompt learning. Recent works demonstrate the performances of 3D point cloud recognition can be boosted remarkably by parameter-efficient prompt tuning. However, we observe that the improvement…
Large Language Models (LLMs) have demonstrated unparalleled efficacy in natural language processing. However, their high computational demands and memory overheads hinder their broad deployment. To address this, two quantization strategies emerge, including Quantization-Aware Training (QAT) and Post…
Zero-shot quantization aims to learn a quantized model from a pre-trained full-precision model with no access to original real training data. The common idea in zero-shot quantization approaches is to generate synthetic data for quantizing the full-precision model. While it is well-known that deep n…
"Large pretrained plain vision Transformers (ViTs) have been the workhorse for many downstream tasks. However, existing works utilizing off-the-shelf ViTs are inefficient in terms of training and deployment, because adopting ViTs with individual sizes requires separate trainings and is restricted by…
"This paper presents a novel approach for surface mesh reconstruction from 3D Gaussian Splatting (3DGS) [?], a technique renowned for its efficiency in novel view synthesis but challenged for surface reconstruction. The key obstacle is the lack of geometry hints to regulate the optimization of milli…
Generative models e.g. Stable Diffusion have enabled the creation of photorealistic images from text prompts. Yet the generation of 360-degree panorama images from text remains a challenge particularly due to the dearth of paired text-panorama data and the domain gap between panorama and perspective…
Efficiently and accurately detecting people from 3D point cloud data is of great importance in many robotic and autonomous driving applications. This fundamental perception task is still very challenging due to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/199
The DETR-like segmentors have underpinned the most recent breakthroughs in semantic segmentation, which end-to-end train a set of queries representing the class prototypes or target segments. Recently, masked attention is proposed to restrict each query to only attend to the foreground regions predi…
Autonomous robotic systems operating in human environments must understand their surroundings to make accurate and safe decisions. In crowded human scenes with close-up human-robot interaction and robot navigation, a deep understanding of surrounding people requires reasoning about human motion and…
Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding box annotations. Natural language supervision is an attractive alternative for its annotation-free attributes and broad…
This paper proposes a self-supervised approach to learn universal facial representations from videos, that can transfer across a variety of facial analysis tasks such as Facial Attribute Recognition (FAR), Facial Expression Recognition (FER), DeepFake Detection (DFD), and Lip Synchronization (LS). O…
In recent years, neural implicit surface reconstruction has emerged as a popular paradigm for multi-view 3D reconstruction. Unlike traditional multi-view stereo approaches, the neural implicit surface-based methods leverage neural networks to represent 3D scenes as signed distance functions (SDFs).…
Visual Parameter-Efficient Fine-Tuning (PEFT) has become a powerful alternative for full fine-tuning so as to adapt pre-trained vision models to downstream tasks, which only tunes a small number of parameters while freezing the vast majority ones to ease storage burden and optimization difficulty. H…
The public model zoo containing enormous powerful pretrained model families (e.g., ResNet/DeiT) has reached an unprecedented scope than ever, which significantly contributes to the success of deep learning. As each model family consists of pretrained models with diverse scales (e.g., DeiT-Ti/S/B), i…
Effectively encoding multi-scale contextual information is crucial for accurate semantic segmentation. Most of the existing transformer-based segmentation models combine features across scales without any selection, where features on sub-optimal scales may degrade segmentation outcomes. Leveraging f…
Learning deep discrete latent presentations offers a promise of better symbolic and summarized abstractions that are more useful to subsequent downstream tasks. Inspired by the seminal Vector Quantized Variational Auto-Encoder (VQ-VAE), most of work in learning deep discrete representations has main…
Bridging global context interactions correctly is important for high-fidelity image completion with large masks. Previous methods attempting this via deep or large receptive field (RF) convolutions cannot escape from the dominance of nearby interactions, which may be inferior. In this paper, we prop…
"Weakly supervised point cloud segmentation, i.e. semantically segmenting a point cloud with only a few labeled points in the whole 3D scene, is highly desirable due to the heavy burden of collecting abundant dense annotations for the model training. However, existing methods remain challenging to a…
Transformer is a transformative framework for deep learning which models sequential data and has achieved remarkable performance on a wide range of tasks, but with high computational and energy cost. To improve its efficiency, a popular choice is to compress the models via binarization which constra…
"Sketch-and-extrude is a common and intuitive modeling process in computer aided design. This paper studies the problem of learning the shape given in the form of point clouds by “inverse” sketch-and-extrude. We present ExtrudeNet, an unsupervised end-to-end network for discovering sketch and extrud…
Vision Transformers (ViTs) have triggered the most recent and significant breakthroughs in computer vision. Their efficient designs are mostly guided by the indirect metric of computational complexity, i.e., FLOPs, which however has a clear gap with the direct metric such as throughput. Thus, we pro…
Learning-based optical flow estimation has been dominated with the pipeline of cost volume with convolutions for flow regression, which is inherently limited to local correlations and thus is hard to address the long-standing challenge of large displacements. To alleviate this, the state-of-the-art…
Transformers have become one of the dominant architectures in deep learning, particularly as a powerful alternative to convolutional neural networks (CNNs) in computer vision. However, Transformer training and inference in previous works can be prohibitively expensive due to the quadratic complexity…
Although two-stage Vector Quantized (VQ) generative models allow for synthesizing high-fidelity and high-resolution images, their quantization operator encodes similar patches within an image into the same index, resulting in a repeated artifact for similar adjacent regions using existing decoder ar…
"Vision-and-Language Navigation (VLN) is a task that an agent is required to follow a language instruction to navigate to the goal position, which relies on the ongoing interactions with the environment during moving. Recent Transformer-based VLN methods have made great progress benefiting from the…
"The neural implicit representation has shown its effectiveness in novel view synthesis and high-quality 3D reconstruction from multi-view images. However, most approaches focus on holistic scene representation yet ignore individual objects inside it, thus limiting potential downstream applications.…
Adversarial training defense (ATD) and virtual adversarial training (VAT) are the two most effective methods to improve model robustness against attacks and model generalization. While ATD is usually applied in robust machine learning, VAT is used in semi-supervised learning and domain adaption. In…
Object proposal generation is an important and fundamental task in computer vision. In this paper, we propose ProposalCLIP, a method towards unsupervised open-category object proposal generation. Unlike previous works which require a large number of bounding box annotations and/or can only generate…
"Image translation and manipulation have gain increasing attention along with the rapid development of deep generative models. Although existing approaches have brought impressive results, they mainly operated in 2D space. In light of recent advances in NeRF-based 3D-aware generative models, we intr…
We present a unified and flexible framework to address the generalized problem of 3D motion synthesis that covers the tasks of motion prediction, completion, interpolation, and spatial-temporal recovery. Since these tasks have different input constraints and various fidelity and diversity requiremen…
We propose an Auto-Parsing Network (APN) to discover and exploit the input data's hidden tree structures for improving the effectiveness of the Transformer-based vision-language systems. Specifically, we impose a Probabilistic Graphical Model (PGM) parameterized by the attention operations on each s…
Generating an interpretable and compact representation of 3D shapes from point clouds is an important and challenging problem. This paper presents CSG-Stump Net, an unsupervised end-to-end network for learning shapes from point clouds and discovering the underlying constituent modeling primitives an…
We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect causes harmful bias that misleads the attention module to focus on the spurious correlations in training data, damaging the m…
We address the problem of domain generalizable object detection, which aims to learn a domain-invariant detector from multiple "seen" domains so that it can generalize well to other "unseen" domains. The generalization ability is crucial in practical scenarios especially when it is difficult to coll…
Optical flow is inherently a 2D search problem, and thus the computational complexity grows quadratically with respect to the search window, making large displacements matching infeasible for high-resolution images. In this paper, we take inspiration from Transformers and propose a new method for hi…
Currently, the state-of-the-art methods treat few-shot semantic segmentation task as a conditional foreground-background segmentation problem, assuming each class is independent. In this paper, we introduce the concept of meta-class, which is the meta information (e.g. certain middle-level features)…
Imbalanced datasets widely exist in practice and are a great challenge for training deep neural models with a good generalization on infrequent classes. In this work, we propose a new rare-class sample generator (RSG) to solve this problem. RSG aims to generate some new samples for rare classes duri…
The recently proposed Visual image Transformers (ViT) with pure attention have achieved promising performance on image recognition tasks, such as image classification. However, the routine of the current ViT model is to maintain a full-length patch sequence during inference, which is redundant and l…
We propose a novel spatially-correlative loss that is simple, efficient, and yet effective for preserving scene structure consistency while supporting large appearance changes during unpaired image-to-image (I2I) translation. Previous methods attempt this by using pixel-level cycle-consistency or fe…
3D instance segmentation plays a predominant role in environment perception of robotics and augmented reality. Many deep learning based methods have been presented recently for this task. These methods rely on either a detection branch to propose objects or a grouping step to assemble same-instance…
Fully supervised object detection has achieved great success in recent years. However, abundant bounding boxes annotations are needed for training a detector for novel classes. To reduce the human labeling effort, we propose a novel webly supervised object detection (WebSOD) method for novel classes…
Change Captioning is a task that aims to describe the difference between images with natural language. Most existing methods treat this problem as a difference judgment without the existence of distractors such as viewpoint changes. However, in practice, viewpoint changes happen often and can overwh…
Despite the great progress in human motion prediction, it remains a challenging task due to the complicated structural dynamics of human behaviors. In this paper, we address this problem in three aspects. First, to capture the long-range spatial correlations and temporal dependencies, we apply a tra…
Despite the huge progress in scene graph generation in recent years, its long-tail distribution in object relationships remains a challenging and pestering issue. Existing methods largely rely on either external knowledge or statistical bias information to alleviate this problem. In this paper, we t…
Structured representations of images that model visual relationships are beneficial for many vision and vision-language applications. However, current human-annotated visual relationship datasets suffer from the long-tailed predicate distribution problem which limits the potential of visual relation…
In this paper we focus on the task of weakly-supervised semantic segmentation supervised with image-level labels. Since the pixel-level annotation is not available in the training process, we rely on region mining models to estimate the pseudo-masks from the image-level labels. Thus, in order to imp…
This work addresses a novel and challenging problem of estimating the full 3D hand shape and pose from a single RGB image. Most current methods in 3D hand analysis from monocular RGB images only focus on estimating the 3D locations of hand keypoints, which cannot fully express the 3D shape of hand.…
We propose Scene Graph Auto-Encoder (SGAE) that incorporates the language inductive bias into the encoder-decoder image captioning framework for more human-like captions. Intuitively, we humans use the inductive bias to compose collocations and contextual inference in discourse. For example, when we…
Despite great progress in 3D pose estimation from single-view images or videos, it remains a challenging task due to the substantial depth ambiguity and severe self-occlusions. Motivated by the effectiveness of incorporating spatial dependencies and temporal consistencies to alleviate these issues,…
We do not speak word by word from scratch; our brain quickly structures a pattern like sth do sth at someplace and then fill in the detailed description. To render existing encoder-decoder image captioners such human-like reasoning, we propose a novel framework: learning to Collocate Neural Modules…
Most image completion methods produce only one result for each masked input, although there may be many reasonable possibilities. In this paper, we present an approach for pluralistic image completion - the task of generating multiple and diverse plausible solutions for image completion. A major cha…
Scene graph generation has received growing attention with the advancements in image understanding tasks such as object detection, attributes and relationship prediction, etc. However, existing datasets are biased in terms of object and relationship labels, or often come with noisy and missing annot…
This work addresses the problem of 3D human shape reconstruction from point clouds. Considering that human shapes are of high dimensions and with large articulations, we adopt the state-of-the-art parametric human body model, SMPL, to reduce the dimension of learning space and generate smooth and va…
Most of current image captioning models heavily rely on paired image-caption datasets. However, getting large scale image-caption paired data is labor-intensive and time-consuming. In this paper, we present a scene graph-based approach for unpaired image captioning. Our framework comprises an image…
Caricature is an art form that expresses subjects in abstract, simple and exaggerated views. While many caricatures are 2D images, this paper presents an algorithm for creating expressive 3D caricatures from 2D caricature images with minimum user interaction. The key idea of our approach is to intro…
Facial action unit (AU) detection and face alignment are two highly correlated tasks since facial landmarks can provide precise AU locations to facilitate the extraction of meaningful local features for AU detection. Most existing AU detection works often treat face alignment as a preprocessing and…
In order to scale standard Gaussian process (GP) regression to large-scale datasets, aggregation models employ factorized training process and then combine predictions from distributed experts. The state-of-the-art aggregation models, however, either provide inconsistent predictions or require time-…
Textual-visual cross-modal retrieval has been a hot research topic in both computer vision and natural language processing communities. Learning appropriate representations for multi-modal data is crucial for the cross-modal retrieval performance. Unlike existing image-text retrieval approaches that…
This paper presents a Quadtree Convolutional Neural Network (QCNN) for efficiently learning from image datasets representing sparse data such as handwriting, pen strokes, freehand sketches, etc. Instead of storing the sparse sketches in regular dense tensors, our method decomposes and represents the…
Due to fact that it is prohibitively expensive to completely annotate visual relationships, ie, the (obj1, rel, obj2) triplets, relationship models are inevitably biased to object classes of limited pairwise patterns, leading to poor generalization to rare or unseen object combinations. Therefore, w…
Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images, that comprises an image translation network for enhancing reali…
Image captioning is a multimodal task involving computer vision and natural language processing, where the goal is to learn a mapping from the image to its natural language description. In general, the mapping function is learned from a training set of image-caption pairs. However, for some language…
Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even more importance compared with the answer itself, since it makes the question an…
Compared with depth-based 3D hand pose estimation, it is more challenging to infer 3D hand pose from monocular RGB images, due to substantial depth ambiguity and the difficulty of obtaining fully-annotated training data. Different from existing learning-based monocular RGB-input approaches that requ…
Object detection is one of the major problems in computer vision, and has been extensively studied. Most of the existing detection works rely on labor-intensive supervision, such as ground truth bounding boxes of objects or at least image-level annotations. On the contrary, we propose an object dete…
We consider the problem of depth-based robust 3D facial pose tracking under unconstrained scenarios with heavy occlusions and arbitrary facial expression variations. Unlike the previous depth-based discriminative or data-driven methods that require sophisticated training or manual intervention, we p…
Language models based on recurrent neural networks have dominated recent image caption generation tasks. In this paper, we introduce a Language CNN model which is suitable for statistical language modeling tasks and shows competitive performance in image captioning. In contrast to previous models wh…
Multi-instance multi-label (MIML) learning has many interesting applications in computer visions, including multi-object recognition and automatic image tagging. In these applications, additional information such as bounding-boxes, image captions and descriptions is often available during training p…
Recent advances in the joint processing of images have certainly shown its advantages over the individual processing. Different from the existing works geared towards co-segmentation or co-localization, in this paper, we explore a new joint processing topic: co-skeletonization, which is defined as j…
Currently most action recognition or video classification tasks highly rely on the motion features such as state-of-the-art Improved Dense Trajectory (IDT) features. Despite the huge success, IDT features lack of rich static object-level information. In this paper, we make use of the object-level fe…
Convolutional neural networks (CNNs) have shown great performance as general feature representations for object recognition applications. However, for multi-label images that contain multiple objects from different categories, scales and locations, global CNN features are not optimal. In this paper,…
While convolutional neural networks (CNN) have been excellent for object recognition, the greater spatial variability in scene images typically meant that the standard full-image CNN features are suboptimal for scene classification. In this paper, we investigate a framework allowing greater spatial…
In this paper, we propose a novel dense correspondence based prediction approach to reduce the inter-image redundancy for image set compression. Unlike previous methods, we manage to utilize the dense correspondence to predict and parameterize the inter-image relation and then reconstruct a new refe…
Most of the feature-learning methods for RGB-D object recognition either learn features from color and depth modalities separately, or simply treat RGB-D as undifferentiated four-channel data, which cannot adequately exploit the relationship between different modalities. Motivated by the intuition t…