63 citations · 272 across the 33 of their papers we have counts for
27 papers · 1 filter
MergeTok: Unified Continuous and Discrete Visual Tokenization via Token Merging
Luyuan Zhang, Siyuan Li, Zedong Wang +7
Most visual tokenizers for image generation are bifurcated into two families with complementary limitations: continuous VAEs offer high-fidelity reconstruction but suffer from dens…
ST-Lite: Training-Free KV Cache Compression with Spatio-Trajectory Guidance for Long-Horizon GUI Agents
Bowen Zhou, Zhou Xu, Wanli Li +3
Training-free KV cache compression is essential for deploying vision-language GUI agents under memory and latency constraints, yet existing methods are designed for generic languag…
DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Prior
Junzhe Lu, Jing Lin, Hongkun Dou +8
We present DPoser-X, a diffusion-based prior model for 3D whole-body human poses. Building a versatile and robust full-body human pose prior remains challenging due to the inherent…
Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios
Huaqiu Li, Xiaowan Hu, Haoqian Wang
Real-world low-light images often suffer from complex degradations such as local overexposure, low brightness, noise, and uneven illumination. Supervised methods tend to overfit to…
HumanMM: Global Human Motion Recovery from Multi-shot Videos
Yuhong Zhang, Guanlin Wu, Ling-Hao Chen +8
In this paper, we present a novel framework designed to reconstruct long-sequence 3D human motion in the world coordinates from in-the-wild videos with multiple shot transitions. S…
Prompt-SID: Learning Structural Representation Prompt via Latent Diffusion for Single-Image Denoising
Huaqiu Li, Wang Zhang, Xiaowan Hu +3
Many studies have concentrated on constructing supervised models utilizing paired datasets for image denoising, which proves to be expensive and time-consuming. Current self-superv…
Motion-X++: A Large-Scale Multimodal 3D Whole-body Human Motion Dataset
Yuhong Zhang, Jing Lin, Ailing Zeng +7
In this paper, we introduce Motion-X++, a large-scale multimodal 3D expressive whole-body human motion dataset. Existing motion datasets predominantly capture body-only poses, lack…
Spatiotemporal Blind-Spot Network with Calibrated Flow Alignment for Self-Supervised Video Denoising
Zikang Chen, Tao Jiang, Xiaowan Hu +3
Self-supervised video denoising aims to remove noise from videos without relying on ground truth data, leveraging the video itself to recover clean frames. Existing methods often r…
TexVocab: Texture Vocabulary-conditioned Human Avatars
Yuxiao Liu, Zhe Li, Yebin Liu +1
To adequately utilize the available image evidence in multi-view video-based avatar modeling, we propose TexVocab, a novel avatar representation that constructs a texture vocabular…
LangSplat: 3D Language Gaussian Splatting
Minghan Qin, Wanhua Li, Jiawei Zhou +2
Humans live in a 3D world and commonly use natural language to interact with a 3D scene. Modeling a 3D language field to support open-ended language queries in 3D has gained increa…
High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field
Minghan Qin, Yifan Liu, Yuelang Xu +3
One crucial aspect of 3D head avatar reconstruction lies in the details of facial expressions. Although recent NeRF-based photo-realistic 3D head avatar methods achieve high-qualit…
GroupLane: End-to-End 3D Lane Detection with Channel-wise Grouping
Zhuoling Li, Chunrui Han, Zheng Ge +5
Efficiency is quite important for 3D lane detection due to practical deployment demand. In this work, we propose a simple, fast, and end-to-end detector that still maintains high d…
Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset
Jing Lin, Ailing Zeng, Shunlin Lu +4
In this paper, we present Motion-X, a large-scale 3D expressive whole-body motion dataset. Existing motion datasets predominantly contain body-only poses, lacking facial expression…
Learning Visibility Field for Detailed 3D Human Reconstruction and Relighting
Ruichen Zheng, Peng Li, Haoqian Wang +1
Detailed 3D reconstruction and photo-realistic relighting of digital humans are essential for various applications. To this end, we propose a novel sparse-view 3d human reconstruct…
VoxelFormer: Bird's-Eye-View Feature Generation based on Dual-view Attention for Multi-view 3D Object Detection
Zhuoling Li, Chuanrui Zhang, Wei-Chiu Ma +5
In recent years, transformer-based detectors have demonstrated remarkable performance in 2D visual perception tasks. However, their performance in multi-view 3D object detection re…
One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
Jing Lin, Ailing Zeng, Haoqian Wang +2
Whole-body mesh recovery aims to estimate the 3D human body, face, and hands parameters from a single image. It is challenging to perform this task with a single network due to res…
3D Face Arbitrary Style Transfer
Xiangwen Deng, Yingshuang Zou, Yuanhao Cai +6
Style transfer of 3D faces has gained more and more attention. However, previous methods mainly use images of artistic faces for style transfer while ignoring arbitrary style image…
Calibrated Teacher for Sparsely Annotated Object Detection
Haohan Wang, Liang Liu, Boshen Zhang +6
Fully supervised object detection requires training images in which all instances are annotated. This is actually impractical due to the high labor and time costs and the unavoidab…
Iterative Few-shot Semantic Segmentation from Image Label Text
Haohan Wang, Liang Liu, Wuhao Zhang +5
Few-shot semantic segmentation aims to learn to segment unseen class objects with the guidance of only a few support images. Most previous methods rely on the pixel-level label of…
Retinexformer: One-stage Retinex-based Transformer for Low-light Image Enhancement
Yuanhao Cai, Hao Bian, Jing Lin +3
When enhancing low-light images, many deep learning algorithms are based on the Retinex theory. However, the Retinex model does not consider the corruptions hidden in the dark or i…
Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration
Jing Lin, Xiaowan Hu, Yuanhao Cai +5
How to properly model the inter-frame relation within the video sequence is an important but unsolved challenge for video restoration (VR). In this work, we propose an unsupervised…
Delving into the Pre-training Paradigm of Monocular 3D Object Detection
Zhuoling Li, Chuanrui Zhang, En Yu +1
The labels of monocular 3D object detection (M3OD) are expensive to obtain. Meanwhile, there usually exists numerous unlabeled data in practical applications, and pre-training is a…
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction
Yuanhao Cai, Jing Lin, Zudi Lin +5
Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image…
Learning to Generate Realistic Noisy Images via Pixel-level Noise-aware Adversarial Training
Yuanhao Cai, Xiaowan Hu, Haoqian Wang +3
Existing deep learning real denoising methods require a large amount of noisy-clean image pairs for supervision. Nonetheless, capturing a real noisy-clean dataset is an unacceptabl…