2.3k citations · 4.3k across the 64 of their papers we have counts for
53 papers · 1 filter
DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction
Yuting Xiao, Jingwei Xu, Zehao Yu +1
In recent years, the neural implicit surface has emerged as a powerful representation for multi-view surface reconstruction due to its simplicity and state-of-the-art performance.…
Revisiting Event-based Video Frame Interpolation
Jiaben Chen, Yichen Zhu, Dongze Lian +7
Dynamic vision sensors or event cameras provide rich complementary information for video frame interpolation. Existing state-of-the-art methods follow the paradigm of combining bot…
Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation
Zibo Zhao, Wen Liu, Xin Chen +7
We present a novel alignment-before-generation approach to tackle the challenging task of generating general 3D shapes based on 2D images or texts. Directly learning a conditional…
InstructP2P: Learning to Edit 3D Point Clouds with Text Instructions
Jiale Xu, Xintao Wang, Yan-Pei Cao +3
Enhancing AI systems to perform tasks following human instructions can significantly boost productivity. In this paper, we present InstructP2P, an end-to-end framework for 3D shape…
Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction
Binbin Huang, Xingyue Peng, Siyuan Shen +8
We introduce Omni-LOS, a neural computational imaging method for conducting holistic shape reconstruction (HSR) of complex objects utilizing a Single-Photon Avalanche Diode (SPAD)-…
Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos
Sixun Dong, Huazhang Hu, Dongze Lian +3
Sequential video understanding, as an emerging video understanding task, has driven lots of researchers' attention because of its goal-oriented nature. This paper studies weakly su…
High-level Feature Guided Decoding for Semantic Segmentation
Ye Huang, Di Kang, Shenghua Gao +2
Existing pyramid-based upsamplers (e.g. SemanticFPN), although efficient, usually produce less accurate results compared to dilation-based models when using the same backbone. This…
PSDF for Neural Indoor Scene Reconstruction
Jing Li, Jinpeng Yu, Ruoyu Wang +4
Given only a set of images, neural implicit surface representation has shown its capability in 3D surface reconstruction. However, as the nature of per-scene optimization is based…
Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Models
Jiale Xu, Xintao Wang, Weihao Cheng +4
Recent CLIP-guided 3D optimization methods, such as DreamFields and PureCLIPNeRF, have achieved impressive results in zero-shot text-to-3D synthesis. However, due to scratch traini…
Lifelong Person Re-Identification via Knowledge Refreshing and Consolidation
Chunlin Yu, Ye Shi, Zimo Liu +2
Lifelong person re-identification (LReID) is in significant demand for real-world development as a large amount of ReID data is captured from diverse locations over time and cannot…
ResNeRF: Geometry-Guided Residual Neural Radiance Field for Indoor Scene Novel View Synthesis
Yuting Xiao, Yiqun Zhao, Yanyu Xu +1
We represent the ResNeRF, a novel geometry-guided two-stage framework for indoor scene novel view synthesis. Be aware of that a good geometry would greatly boost the performance of…
PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes
Ruoyu Wang, Zehao Yu, Shenghua Gao
Multiple near frontal-parallel planes based depth representation demonstrated impressive results in self-supervised monocular depth estimation (MDE). Whereas, such a representation…
Dual-Space NeRF: Learning Animatable Avatars and Scene Lighting in Separate Spaces
Yihao Zhi, Shenhan Qian, Xinhao Yan +1
Modeling the human body in a canonical space is a common practice for capturing and animation. But when involving the neural radiance field (NeRF), learning a static NeRF in the ca…
UNIF: United Neural Implicit Functions for Clothed Human Reconstruction and Animation
Shenhan Qian, Jiale Xu, Ziwei Liu +2
We propose united implicit functions (UNIF), a part-based method for clothed human reconstruction and animation with raw scans and skeletons as the input. Previous part-based metho…
PREF: Phasorial Embedding Fields for Compact Neural Representations
Binbin Huang, Xinhao Yan, Anpei Chen +2
We present an efficient frequency-based neural representation termed PREF: a shallow MLP augmented with a phasor volume that covers significant border spectra than previous Fourier…
DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers
Xianing Chen, Qiong Cao, Yujie Zhong +3
Transformers are successfully applied to computer vision due to their powerful modeling capacity with self-attention. However, the excellent performance of transformers heavily dep…
TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting
Huazhang Hu, Sixun Dong, Yiqun Zhao +3
Counting repetitive actions are widely seen in human activities such as physical exercise. Existing methods focus on performing repetitive action counting in short videos, which is…
Taylor3DNet: Fast 3D Shape Inference With Landmark Points Based Taylor Series
Yuting Xiao, Jiale Xu, Shenghua Gao
Benefiting from the continuous representation ability, deep implicit functions can represent a shape at infinite resolution. However, extracting high-resolution iso-surface from an…
SVIP: Sequence VerIfication for Procedures in Videos
Yicheng Qian, Weixin Luo, Dongze Lian +3
In this paper, we propose a novel sequence verification task that aims to distinguish positive video pairs performing the same action sequence from negative ones with step-level tr…
MOS: A Low Latency and Lightweight Framework for Face Detection, Landmark Localization, and Head Pose Estimation
Yepeng Liu, Zaiwang Gu, Shenghua Gao +3
With the emergence of service robots and surveillance cameras, dynamic face recognition (DFR) in wild has received much attention in recent years. Face detection and head pose esti…
Cross-domain Trajectory Prediction with CTP-Net
Pingxuan Huang, Zhenhua Cui, Jing Li +3
Most pedestrian trajectory prediction methods rely on a huge amount of trajectories annotation, which is time-consuming and expensive. Moreover, a well-trained model may not effect…
OH-Former: Omni-Relational High-Order Transformer for Person Re-Identification
Xianing Chen, Chunlin Xu, Qiong Cao +6
Transformers have shown preferable performance on many vision tasks. However, for the task of person re-identification (ReID), vanilla transformers leave the rich contexts on high-…
Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates
Shenhan Qian, Zhi Tu, Yihao Zhi +2
Co-speech gesture generation is to synthesize a gesture sequence that not only looks real but also matches with the input speech audio. Our method generates the movements of a comp…
AS-MLP: An Axial Shifted MLP Architecture for Vision
Dongze Lian, Zehao Yu, Xing Sun +1
An Axial Shifted MLP architecture (AS-MLP) is proposed in this paper. Different from MLP-Mixer, where the global spatial feature is encoded for information flow through matrix tran…