32 citations · 67 across the 23 of their papers we have counts for
27 papers
3EED: Ground Everything Everywhere in 3D
Rong Li, Yuhao Dong, Tianshuai Hu +7
Visual grounding in 3D is the key for embodied agents to localize language-referred objects in open-world environments. However, existing benchmarks are limited to indoor focus, si…
See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
Dongyue Lu, Ao Liang, Tianxin Huang +8
Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video-to-4D methods typically rely on manually ann…
Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity
Yuhan Zhang, Long Zhuo, Ziyang Chu +5
Despite rapid advances in 3D content generation, quality assessment for the generated 3D assets remains challenging. Existing methods mainly rely on image-based metrics and operate…
Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining
Xiang Xu, Lingdong Kong, Hui Shuai +5
LiDAR representation learning has emerged as a promising approach to reducing reliance on costly and labor-intensive human annotations. While existing methods primarily focus on sp…
Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives
Shaoyuan Xie, Lingdong Kong, Yuhao Dong +5
Recent advancements in Vision-Language Models (VLMs) have sparked interest in their use for autonomous driving, particularly in generating interpretable driving decisions through n…
LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving
Lingdong Kong, Xiang Xu, Youquan Liu +6
Recent advancements in vision foundation models (VFMs) have revolutionized visual perception in 2D, yet their potential for 3D scene understanding, particularly in autonomous drivi…
LiMoE: Mixture of LiDAR Representation Learners from Automotive Scenes
Xiang Xu, Lingdong Kong, Hui Shuai +3
LiDAR data pretraining offers a promising approach to leveraging large-scale, readily available datasets for enhanced data utilization. However, existing methods predominantly focu…
OVGaussian: Generalizable 3D Gaussian Segmentation with Open Vocabularies
Runnan Chen, Xiangyu Sun, Zhaoqing Wang +8
Open-vocabulary scene understanding using 3D Gaussian (3DGS) representations has garnered considerable attention. However, existing methods mostly lift knowledge from large 2D visi…
MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D
Wei Cheng, Juncheng Mu, Xianfang Zeng +8
Texturing is a crucial step in the 3D asset production workflow, which enhances the visual appeal and diversity of 3D assets. Despite recent advancements in Text-to-Texture (T2T) g…
GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data
Wentao Wang, Hang Ye, Fangzhou Hong +5
Given a single in-the-wild human photo, it remains a challenging task to reconstruct a high-fidelity 3D human model. Existing methods face difficulties including a) the varying bod…
AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation
Yukang Cao, Liang Pan, Kai Han +2
Recent advancements in diffusion models have led to significant improvements in the generation and animation of 4D full-body human-object interactions (HOI). Nevertheless, existing…
GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting
Yukang Cao, Masoud Hadi, Liang Pan +1
Diffusion-based 2D virtual try-on (VTON) techniques have recently demonstrated strong performance, while the development of 3D VTON has largely lagged behind. Despite recent advanc…
DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes
Hengwei Bian, Lingdong Kong, Haozhe Xie +3
Urban scene generation has been developing rapidly recently. However, existing methods primarily focus on generating static and single-frame scenes, overlooking the inherently dyna…
3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion
Zhaoxi Chen, Jiaxiang Tang, Yuhao Dong +10
The increasing demand for high-quality 3D assets across various industries necessitates efficient and automated 3D content creation. Despite recent advancements in 3D generative mo…
Point Transformer V3 Extreme: 1st Place Solution for 2024 Waymo Open Dataset Challenge in Semantic Segmentation
Xiaoyang Wu, Xiang Xu, Lingdong Kong +5
In this technical report, we detail our first-place solution for the 2024 Waymo Open Dataset Challenge's semantic segmentation track. We significantly enhanced the performance of P…
4D Contrastive Superflows are Dense 3D Representation Learners
Xiang Xu, Lingdong Kong, Hui Shuai +5
In the realm of autonomous driving, accurate 3D perception is the foundation. However, developing such models relies on extensive human annotations -- a process that is both costly…
The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
Lingdong Kong, Shaoyuan Xie, Hanjiang Hu +88
In the realm of autonomous driving, robust perception under out-of-distribution conditions is paramount for the safe deployment of vehicles. Challenges such as adverse weather, sen…
DiffTF++: 3D-aware Diffusion Transformer for Large-Vocabulary 3D Generation
Ziang Cao, Fangzhou Hong, Tong Wu +2
Generating diverse and high-quality 3D assets automatically poses a fundamental yet challenging task in 3D computer vision. Despite extensive efforts in 3D generation, existing opt…
Multi-Space Alignments Towards Universal LiDAR Segmentation
Youquan Liu, Lingdong Kong, Xiaoyang Wu +5
A unified and versatile LiDAR segmentation model with strong robustness and generalizability is desirable for safe autonomous driving perception. This work presents M3Net, a one-of…
Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving
Shaoyuan Xie, Lingdong Kong, Wenwei Zhang +4
Recent advancements in bird's eye view (BEV) representations have shown remarkable promise for in-vehicle 3D perception. However, while these methods have achieved impressive resul…
Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
Lingdong Kong, Xiang Xu, Jiawei Ren +5
Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supe…
Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding
Lingdong Kong, Xiang Xu, Jun Cen +4
Safety-critical 3D scene understanding tasks necessitate not only accurate but also confident predictions from 3D perception models. This study introduces Calib3D, a pioneering eff…
3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
Fangzhou Hong, Jiaxiang Tang, Ziang Cao +8
We present a two-stage text-to-3D generation system, namely 3DTopia, which generates high-quality general 3D assets within 5 minutes using hybrid diffusion priors. The first stage…
Exploiting Hierarchical Interactions for Protein Surface Learning
Yiqun Lin, Liang Pan, Yi Li +2
Predicting interactions between proteins is one of the most important yet challenging problems in structural bioinformatics. Intrinsically, potential function sites in protein surf…