33 accepted papers
Class-Incremental Learning (CIL) aims to continually learn new classes without forgetting previously acquired knowledge. Vision-language models such as CLIP offer strong transferable representations via multi-modal supervision, making them a promising choice for CIL. However, applying CLIP to CIL po
We present MoVieS, a Motion-aware View Synthesis model that reconstructs 4D dynamic scenes from monocular videos in one second. It represents dynamic 3D scenes with pixel-aligned Gaussian primitives and explicitly supervises their time-varying motions. This allows, for the first time, the unified mo
The ability to accurately assess and anticipate risks in safety-critical scenarios is crucial for autonomous driving systems. While existing research has made progress in collision prediction, accurately quantifying risk levels from monocular vision inputs remains challenging due to the complex dyna…
Vision-Language Models (VLMs) are limited by static knowledge and insufficient fine-grained visual analysis, hindering their performance on knowledge-intensive and visually complex tasks. While recent research has explored VLMs that employ external tools like search or cropping to enhance model perf
This paper proposes a new turning theory for spherical robots, which better describes the turning mechanism of spherical robots under turning constraints, using a pendulum-driven spherical robot as an example. Compared to the previous turning theory, the new theory shows greater alignment with real-
Low-Light Video Enhancement (LLVE) seeks to restore dynamic or static scenes plagued by severe invisibility and noise. In this paper, we present an innovative video decomposition strategy that incorporates view-independent and view-dependent components to enhance the performance of LLVE. We leverage
We propose PRM, a novel photometric stereo based large reconstruction model to reconstruct high-quality meshes with fine-grained details. Previous large reconstruction models typically prepare training images under fixed and simple lighting, offering minimal photometric cues for precise reconstructi…
Scene-aware Adaptive Compressive Sensing (ACS) has attracted significant interest due to its promising capability for efficient and high-fidelity acquisition of scene images. ACS typically prescribes adaptive sampling allocation (ASA) based on previous samples in the absence of ground truth. However…
Open-vocabulary semantic segmentation (OVSS) is a challenging computer vision task that labels each pixel within an image based on text descriptions. Recent advancements in OVSS are largely attributed to the increased model capacity. However, these models often struggle with unfamiliar images or uns…
Pre-trained models with large-scale training data such as CLIP and Stable Diffusion have demonstrated remarkable performance in various high-level computer vision tasks such as image understanding and generation from language descriptions. Yet their potential for low-level tasks such as image restor…
High Dynamic Range (HDR) images can be reconstructed from multiple Low Dynamic Range (LDR) images using existing deep neural network (DNN) techniques. Despite notable advancements, DNN-based methods still exhibit ghosting artifacts when handling LDR images with saturation and significant motion. Rec…
While recent progress in Multi-exposure HDR imaging is promising, the growing complexity of state-of-the-art (SOTA) methods poses challenges for their analysis and comparison. In this paper, we analyze the motivations and approaches behind previous SOTA works and introduce EiffHDR, an efficient Mult…
RAW to sRGB mapping, which aims to convert RAW images from smartphones into RGB form equivalent to that of Digital Single-Lens Reflex (DSLR) cameras, has become an important area of research. However, current methods often ignore the difference between cell phone RAW images and DSLR camera RGB image…
We present GauHuman a 3D human model with Gaussian Splatting for both fast training (1 2 minutes) and real-time rendering (up to 189 FPS) compared with existing NeRF-based implicit representation modelling frameworks demanding hours of training and seconds of rendering per frame. Specifically GauHum…
Recovering ghost-free High Dynamic Range (HDR) images from multiple Low Dynamic Range (LDR) images becomes challenging when the LDR images exhibit saturation and significant motion. Recent Diffusion Models (DMs) have been introduced in HDR imaging field demonstrating promising performance particular…
"Recent 3D human generative models have achieved remarkable progress by learning 3D-aware GANs from 2D images. However, existing 3D human generative methods model humans in a compact 1D latent space, ignoring the articulated structure and semantics of human body topology. In this paper, we explore m…
Dynamic human rendering from video sequences has achieved remarkable progress by formulating the rendering as a mapping from static poses to human images. However existing methods focus on the human appearance reconstruction of every single frame while the temporal motion relations are not fully exp…
We introduce X-Ray, a novel 3D sequential representation inspired by the penetrability of x-ray scans. X-Ray transforms a 3D object into a series of surface frames at different layers, making it suitable for generating 3D models from images. Our method utilizes ray casting from the camera center to…
Neural radiance fields(NeRF) show great success in novel-view synthesis. However, in real-world scenes, recovering high-quality details from the source images is still challenging for the existing NeRF-based approaches, due to the potential imperfect calibration information and scene representation…
Synthesizing photo-realistic images from a point cloud is challenging because of the sparsity of point cloud representation. Recent Neural Radiance Fields and extensions are proposed to synthesize realistic images from 2D input. In this paper, we present Point2Pix as a novel point renderer to link t…
Neural implicit surface learning has shown significant progress in multi-view 3D reconstruction, where an object is represented by multilayer perceptrons that provide continuous implicit surface representation and view-dependent radiance. However, current methods often fail to accurately reconstruct…
Existing learning-based methods for point cloud rendering adopt various 3D representations and feature querying mechanisms to alleviate the sparsity problem of point clouds. However, artifacts still appear in the rendered images, due to the challenges in extracting continuous and discriminative 3D f…
A spherical robot is a nonlinear, nonholonomic, and unstable system which increases the difficulty of the direction and trajectory tracking problem. In this study, we propose a new direction controller Hierarchical Terminal Sliding Mode Controller (HTSMC), an instruction planning controller called M
Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes. It takes long per-scene training time and per-image testing time. In this paper, we present EfficientNeRF as an efficient NeRF-based method to represent 3D scene and synthesize no…
This work proposes a novel unsupervised cross-modality adaptive segmentation method for medical images to tackle the performance degradation caused by the severe domain shift when neural networks are being deployed to unseen modalities. The proposed method is an end-2-end framework, which conducts a…
Human-Object Interaction Detection tackles the problem of joint localization and classification of human object interactions. Existing HOI transformers either adopt a single decoder for triplet prediction, or utilize two parallel decoders to detect individual objects and interactions separately, and…
While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares weights on the channel dimension. We propose MixFormer to find a…
One controller cannot work on multiple and unknown terrains in the velocity control of the spherical robot, because the dynamic models of the robot vary on different terrains, and unmodeled dynamics and uncertainties exist in estimated dynamic models. Based on the above problem, a new velocity contr
We present EgoRenderer, a system for rendering full-body neural avatars of a person captured by a wearable, egocentric fisheye camera that is mounted on a cap or a VR headset. Our system renders photorealistic novel views of the actor and her motion from arbitrary virtual camera locations. Rendering…
In this paper, a fuzzy PID controller based on yaw angle prediction is applied to design an attitude controller for a spherical rolling robot. The robot consists of a 2-DOF pendulum located inside a spherical shell with freedom to rotate about the transversal and longitudinal axis. The proposed cont…
Recent single-view 3D reconstruction methods reconstruct object's shape and texture from a single image with only 2D image-level annotation. However, without explicit 3D attribute-level supervision, it is still difficult to achieve satisfying reconstruction accuracy. In this paper, we propose a Self…
Few-shot learning is a nascent research topic, motivated by the fact that traditional deep learning requires tremendous amounts of data. In this work, we propose a new task along this research direction, we call few-shot common-localization. Given a few weakly-supervised support images, we aim to lo…
Natural stimuli are highly redundant, possessing significant spatial and temporal correlations. While sparse coding has been proposed as an efficient strategy employed by neural systems to encode sensory stimuli, the underlying mechanisms are still not well understood. Most previous approaches model…