56 accepted papers
While 3D Gaussian Splatting (3DGS) excels at real-time rendering of standard scenes, it struggles to reconstruct underwater environments due to severe challenges such as light scattering, color attenuation, and sparse coverage of Gaussian kernels in far-field aqueous regions. To address this, we int
High-fidelity 3D generation remains difficult. Although some methods have proposed converting raw meshes to SDFs, it remains a lossy process. TripoSF presented a VAE training paradigm based on a rendering loss to circumvent this lossy SDF conversion, achieving high-precision surface reconstruction. …
Diffusion strategies have advanced visual motor control by progressively denoising high-dimensional action sequences, providing a promising method for robot manipulation. However, as task complexity increases, the success rate of existing baseline models decreases considerably. Analysis indicates th
Geometric analysis fundamentally distinguishes between extrinsic and intrinsic perspectives. The dominant paradigm in current 3D representation learning relies on either extrinsic spatial structures or high-level semantics, struggling to capture the essence of shape identity and underlying manifold …
Self-supervised learning (SSL) for point cloud pre-training has become a cornerstone for many 3D vision tasks, enabling effective learning from large-scale unannotated data. At the scene level, existing SSL methods often incorporate volume rendering into the pre-training framework, using RGB-D image…
Recovering precise surface geometry from corrupted point clouds remains a core challenge in 3D vision. Although existing denoising techniques achieve remarkable success, balancing noise removal with preserving intricate geometric details continues to pose difficulties. A critical limitation of curre
Computing geodesic distances on 3D surfaces is fundamental to many tasks in 3D vision and geometry processing, with deep connections to tasks such as shape correspondence. Recent learning-based methods achieve strong performance but rely on large 3D backbones, leading to high memory usage and latenc
Neural Signed Distance Functions (SDFs) excel at reconstructing watertight manifolds but fail on thin structures and open boundaries due to strict inside-outside constraints. Conversely, Unsigned Distance Fields (UDFs) accommodate general geometries but suffer from gradient singularities at the zero…
Reconstructing realistic 3D human avatars from monocular videos is a challenging task due to the limited geometric information and complex non-rigid motion involved. We present MonoCloth, a new method for reconstructing and animating clothed human avatars from monocular videos. To overcome the limit
Reinforcement Fine-tuning (RFT) methods such as Group Relative Policy Optimization (GRPO) have demonstrated strong capabilities in aligning Large Language Models with human preferences. However, these approaches often suffer from limited data efficiency, necessitating extensive on-policy rollouts to
Despite recent advances in retrieval-augmented generation (RAG) for video understanding, effectively understanding long-form video content remains underexplored due to the vast scale and high complexity of video data. Current RAG approaches typically segment videos into fixed-length chunks, which of…
Test-time policy adaptation for multi-turn interactions (T$^2$PAM) is essential for aligning Large Language Models (LLMs) with dynamic user needs during inference time. However, existing paradigms commonly treat test-time adaptation as a single-axis problem, either purely refining instructions (Prom…
Noise is an inevitable aspect of point cloud acquisition, necessitating filtering as a fundamental task within the realm of 3D vision. Existing learning-based filtering methods have shown promising capabilities on commonly used datasets. Nonetheless, the effectiveness of these methods is constrained…
Unsigned distance fields (UDFs) provide a versatile framework for representing a diverse array of 3D shapes, encompassing both watertight and non-watertight geometries. Traditional UDF learning methods typically require extensive training on large 3D shape datasets, which is costly and necessitates…
Inderscience is a global company, a dynamic leading independent journal publisher disseminates the latest research across the broad fields of science, engineering and technology; management, public and business administration; environment, ecological economics and sustainable development; computing,…
In this paper we study the task of a single-view image-guided point cloud completion. Existing methods have got promising results by fusing the information of image into point cloud explicitly or implicitly. However, given that the image has global shape information and the partial point cloud has r…
While Signed Distance Fields (SDF) are well-established for modeling watertight surfaces, Unsigned Distance Fields (UDF) broaden the scope to include open surfaces and models with complex inner structures. Despite their flexibility, UDFs encounter significant challenges in high-fidelity 3D reconstru…
While 3D head reconstruction is widely used for modeling, existing neural reconstruction approaches rely on high-resolution multi-view images, posing notable privacy issues. Individuals are particularly sensitive to facial features, and facial image leakage can lead to many malicious activities, suc…
Recent advancements in implicit 3D reconstruction methods, e.g., neural rendering fields and Gaussian splatting, have primarily focused on novel view synthesis of static or dynamic objects with continuous motion states. However, these approaches struggle to efficiently model a human-interactive obje
We introduce MIRReS, a novel two-stage inverse rendering framework that jointly reconstructs and optimizes explicit geometry, materials, and lighting from multi-view images. Unlike previous methods that rely on implicit irradiance fields or oversimplified ray tracing, our method begins with an initi…
Predicting the future motion of road participants is a critical task in autonomous driving. In this work, we address the challenge of low-quality generation of low-probability modes in multi-agent joint prediction. To tackle this issue, we propose a two-stage multi-agent interactive prediction frame
Novel view synthesis (NVS) and surface reconstruction (SR) are essential tasks in 3D Gaussian Splatting (3DGS). Despite recent progress, these tasks are often addressed independently, with GS-based rendering methods struggling under diverse light conditions and failing to produce accurate surfaces,…
Unsigned distance fields (UDFs) are widely used in 3D deep learning due to their ability to represent shapes with arbitrary topology. While prior work has largely focused on learning UDFs from point clouds or multi-view images, extracting meshes from UDFs remains challenging, as the learned fields r…
Fine-tuning large language models (LLMs) often causes overfitting to specific prompt wording, where minor phrasing variations drastically reduce performance. To address this, we propose Prompt-Agnostic Fine-Tuning (PAFT), a method that enhances robustness through dynamic prompt variation during trai
The latest Segment Anything Model enables realtime scene annotation and understanding for autonomous driving systems, enhancing driving safety. However, effectively allocating resources for real-time performance and accuracy remains challenging in edge-cloud architectures. Traditional reinforcement…
In this study, we introduce a novel two-stage technique for decomposing and reconstructing facial features from sparse-view images, a task made challenging by the unique geometry and complex skin reflectance of each individual. To synthesize 3D facial models more realistically, we endeavor to decoup…
This research aims to enhance the interaction between humans and robots, especially in environments with multiple similar objects or semantic ambiguities. Traditional command-based interactions typically require users to provide precise descriptions, which often poses a significant challenge. To add
Reconstruction from multi-view images is a fundamental challenge in computer vision that has been extensively studied over the past decades. Recently, neural radiance fields have driven significant advancements, especially through methods using implicit functions and volume rendering, achieving high…
Point clouds have become the preferred data format for a variety of tasks in 3D vision and graphics. However, raw point clouds often contain significant noise. This paper introduces the Adaptive Stop Denoising Network (ASDN), a novel approach aimed at restoring high-quality point clouds from noisy d…
Recently building on the foundation of neural radiance field various techniques have emerged to learn unsigned distance fields (UDF) to reconstruct 3D non-watertight models from multi-view images. Yet a central challenge in UDF-based volume rendering is formulating a proper way to convert unsigned d…
Accurate perception of semantic and spatial information is crucial for robots performing language-driven navigation tasks. Existing approaches utilize visual-language models to extract semantic information from the environment and construct maps. However, constrained by the generalization and accura…
Vision-language models (VLMs) show promising generalization and zero-shot capabilities, offering a potential solution to the impracticality and cost of enabling robots to comprehend diverse human instructions and scene semantics in the real world. Existing approaches most directly integrate the sema…
Surface parameterization plays an essential role in numerous computer graphics and geometry processing applications. Traditional parameterization approaches are designed for high-quality meshes laboriously created by specialized 3D modelers, thus unable to meet the processing demand for the current…
Traditional 3D shape reconstruction techniques from multi-view images, such as structure from motion and multi-view stereo, face challenges in reconstructing transparent objects. Recent advances in neural radiance fields and its variants primarily address opaque or transparent objects, encountering…
In 3D object manipulation, collecting expert data for end-to-end imitation learning becomes a mainstream method. Though successful, previous works neglect the guiding role of language in action execution. These methods lack the understanding of action semantics, in which multiple action sequences ar…
"Human motion generation, a cornerstone technique in animation and video production, has widespread applications in various tasks like text-to-motion and music-to-dance. Previous works focus on developing specialist models tailored for each task without scalability. In this work, we present Large Mo…
The autonomous driving community is highly interested in 3D occupancy prediction due to its outstanding geometric perception and object recognition capabilities. However, previous methods are limited to existing semantic conversion mechanisms for solving sparse ground truths problem, causing excessi…
Occlusion is a common issue in 3D reconstruction from RGB-D videos, often blocking the complete reconstruction of objects and presenting an ongoing problem. In this paper, we propose a novel framework, empowered by a 2D diffusion-based in-painting model, to reconstruct complete surfaces for the hidd…
Personalized motion planning holds significant importance within urban automated driving, catering to the unique requirements of individual users. Nevertheless, prior endeavors have frequently encountered difficulties in simultaneously addressing two crucial aspects: personalized planning within int…
Generic object detection methods have achieved preferable results, but it is still challenging to detect objects from complicated traffic scenes like extreme illumination and adverse weather. The existing methods are not robust enough to be extended to new complex traffic scenes. To address this iss…
Reconstructing 3D human heads in low-view settings presents technical challenges, mainly due to the pronounced risk of overfitting with limited views and high-frequency signals. To address this, we propose geometry decomposition and adopt a two-stage, coarse-to-fine training strategy, allowing for p…
We present a learning-based method, namely GeoUDF, to tackle the long-standing and challenging problem of reconstructing a discrete surface from a sparse point cloud. To be specific, we propose a geometry-guided learning method for UDF and its gradient estimation that explicitly formulates the unsig…
The quality of point clouds is often limited by noise introduced during their capture process. Consequently, a fundamental 3D vision task is the removal of noise, known as point cloud filtering or denoising. State-of-the-art learning based methods focus on training neural networks to infer filtered…
Geodesics play a critical role in many geometry processing applications. Traditional algorithms for computing geodesics on 3D mesh models are often inefficient and slow, which make them impractical for scenarios requiring extensive querying of arbitrary point-to-point geodesics. Recently, deep impli…
Arbitrary-scale image super-resolution (SR) is often tackled using the implicit neural representation (INR) approach, which relies on a position encoding scheme to improve its representation ability. In this paper, we introduce orthogonal position encoding (OPE), an extension of position encoding, a…
The emergence of Neural Radiance Fields (NeRF) has promoted the development of synthesized high-fidelity views of the intricate real world. However, it is still a very demanding task to repaint the content in NeRF. In this paper, we propose a novel framework that can take RGB images as input and alt…
"Generating stylized audio-driven gestures for robots and virtual avatars has attracted increasing considerations recently. Existing methods require style labels (e.g. speaker identities), or complex preprocessing of the data to obtain style control parameters. In this paper, we propose a new end-to…
This paper investigates the problem of temporally interpolating dynamic 3D point clouds with large non-rigid deformation. We formulate the problem as estimation of point-wise trajectories (i.e., smooth curves) and further reason that temporal irregularity and under-sampling are two major challenges.…
Deep reinforcement learning (DRL) has been studied in a variety of challenging decision-making tasks, e.g., autonomous driving. \textcolor{black}{However, DRL typically suffers from the action shaking problem, which means that agents can select actions with big difference even though states only sli…
Motivated by the intuition that one can transform two aligned point clouds to each other more easily and meaningfully than a misaligned pair, we propose CorrNet3D -the first unsupervised and end-to-end deep learning-based framework - to drive the learning of dense correspondence between 3D shapes by…
In this paper, we propose a novel deep neural network based method, called PUGeo-Net, for upsampling 3D point clouds. PUGeo-Net incorporates discrete differential geometry into deep learning elegantly by learning the first and second fundamental forms that are able to fully represent the local geome…
State-of-the-art researches model the data of images and videos as low-dimensional manifolds and generate superpixels/supervoxels in a content-sensitive way, which is achieved by computing geodesic centroidal Voronoi tessellation (GCVT) on manifolds. However, computing exact GCVTs is slow due to com…
Sparse signal representation has proven to be an extremely powerful tool in a wide range of engineering applications. However, most of the existing techniques are designed for regular data (such as audio signals and images/videos) that uniformly lies in regular Euclidian spaces. This paper aims at e…
We present a delta DLP 3D printer with large size in this paper. Compared with traditional DLP 3D printers that use a low-cost off-the-shelf consumer projector and a single vertical carriage, the platform of our delta DLP 3D printer can also move horizontally in the plane. We show that this structur…
Superpixels are perceptually meaningful atomic regions that can effectively capture image features. Among various methods for computing uniform superpixels, simple linear iterative clustering (SLIC) is popular due to its simplicity and high performance. In this paper, we extend SLIC to compute conte…