23 citations · 83 across the 27 of their papers we have counts for
27 papers · 1 filter
Position Forcing: Self-Conditioning 3D Generation
Ziheng Ouyang, Zeqiang Lai, Jiarui Chen +7
Recent single-stage 3D generative models commonly adopt VecSet representations, encoding 3D shapes as unordered sets of latent tokens. However, compared with two-stage methods that…
Utonia: Toward One Encoder for All Point Clouds
Yujia Zhang, Xiaoyang Wu, Yunhan Yang +6
We dream of a future where point clouds from all domains can come together to shape a single model that benefits them all. Toward this goal, we present Utonia, a first step toward…
Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations
Yujia Zhang, Xiaoyang Wu, Yixing Lao +4
Humans learn abstract concepts through multisensory synergy, and once formed, such representations can often be recalled from a single modality. Inspired by this principle, we intr…
Generalized Decoupled Learning for Enhancing Open-Vocabulary Dense Perception
Junjie Wang, Keyu Chen, Yulin Li +4
Dense visual perception tasks have been constrained by their reliance on predefined categories, limiting their applicability in real-world scenarios where visual concepts are unbou…
LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans
Zhening Huang, Xiaoyang Wu, Fangcheng Zhong +3
We propose LiteReality, a novel pipeline that converts RGB-D scans of indoor environments into compact, realistic, and interactive 3D virtual replicas. LiteReality not only reconst…
Sonata: Self-Supervised Learning of Reliable Point Representations
Xiaoyang Wu, Daniel DeTone, Duncan Frost +7
In this paper, we question whether we have a reliable self-supervised point cloud model that can be used for diverse 3D tasks via simple linear probing, even with limited data and…
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…
Tailor3D: Customized 3D Assets Editing and Generation with Dual-Side Images
Zhangyang Qi, Yunhan Yang, Mengchen Zhang +7
Recent advances in 3D AIGC have shown promise in directly creating 3D objects from text and images, offering significant cost savings in animation and product design. However, deta…
Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splatting
Zheng Zhang, Wenbo Hu, Yixing Lao +2
3D Gaussian Splatting (3DGS) has demonstrated impressive novel view synthesis results while advancing real-time rendering performance. However, it relies heavily on the quality of…
OpenSUN3D: 1st Workshop Challenge on Open-Vocabulary 3D Scene Understanding
Francis Engelmann, Ayca Takmaz, Jonas Schult +25
This report provides an overview of the challenge hosted at the OpenSUN3D Workshop on Open-Vocabulary 3D Scene Understanding held in conjunction with ICCV 2023. The goal of this wo…
Towards Unified 3D Object Detection via Algorithm and Data Unification
Zhuoling Li, Xiaogang Xu, SerNam Lim +1
Realizing unified 3D object detection, including both indoor and outdoor scenes, holds great importance in applications like robot navigation. However, involving various scenarios…
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Lihe Yang, Bingyi Kang, Zilong Huang +3
This work presents Depth Anything, a highly practical solution for robust monocular depth estimation. Without pursuing novel technical modules, we aim to build a simple yet powerfu…
A Lightweight Clustering Framework for Unsupervised Semantic Segmentation
Yau Shing Jonathan Cheung, Xi Chen, Lihe Yang +1
Unsupervised semantic segmentation aims to categorize each pixel in an image into a corresponding class without the use of annotated data. It is a widely researched area as obtaini…
Gemini vs GPT-4V: A Preliminary Comparison and Combination of Vision-Language Models Through Qualitative Cases
Zhangyang Qi, Ye Fang, Mengchen Zhang +6
The rapidly evolving sector of Multi-modal Large Language Models (MLLMs) is at the forefront of integrating linguistic and visual processing in artificial intelligence. This paper…
Self-supervised Learning for Enhancing Geometrical Modeling in 3D-Aware Generative Adversarial Network
Jiarong Guo, Xiaogang Xu, Hengshuang Zhao
3D-aware Generative Adversarial Networks (3D-GANs) currently exhibit artifacts in their 3D geometrical modeling, such as mesh imperfections and holes. These shortcomings are primar…
CorresNeRF: Image Correspondence Priors for Neural Radiance Fields
Yixing Lao, Xiaogang Xu, Zhipeng Cai +2
Neural Radiance Fields (NeRFs) have achieved impressive results in novel view synthesis and surface reconstruction tasks. However, their performance suffers under challenging scena…
LivePhoto: Real Image Animation with Text-guided Motion Control
Xi Chen, Zhiheng Liu, Mengting Chen +4
Despite the recent progress in text-to-video generation, existing studies usually overlook the issue that only spatial contents but not temporal motions in synthesized videos are u…
Point Transformer V3: Simpler, Faster, Stronger
Xiaoyang Wu, Li Jiang, Peng-Shuai Wang +6
This paper is not motivated to seek innovation within the attention mechanism. Instead, it focuses on overcoming the existing trade-offs between accuracy and efficiency within the…
TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation
Rongkun Zheng, Lu Qi, Xi Chen +4
Training on large-scale datasets can boost the performance of video instance segmentation while the annotated datasets for VIS are hard to scale up due to the high labor cost. What…
DreamComposer: Controllable 3D Object Generation via Multi-View Conditions
Yunhan Yang, Yukun Huang, Xiaoyang Wu +5
Utilizing pre-trained 2D large-scale generative models, recent works are capable of generating high-quality novel views from a single in-the-wild image. However, due to the lack of…
GPT4Point: A Unified Framework for Point-Language Understanding and Generation
Zhangyang Qi, Ye Fang, Zeyi Sun +5
Multimodal Large Language Models (MLLMs) have excelled in 2D image-text comprehension and image generation, but their understanding of the 3D world is notably deficient, limiting p…
Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding
Zhihao Yuan, Jinke Ren, Chun-Mei Feng +3
3D Visual Grounding (3DVG) aims at localizing 3D object based on textual descriptions. Conventional supervised methods for 3DVG often necessitate extensive annotations and a predef…
FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models
Lihe Yang, Xiaogang Xu, Bingyi Kang +2
Semantic segmentation has witnessed tremendous progress due to the proposal of various advanced network architectures. However, they are extremely hungry for delicate annotations t…
Uni3DETR: Unified 3D Detection Transformer
Zhenyu Wang, Yali Li, Xi Chen +2
Existing point cloud based 3D detectors are designed for the particular scene, either indoor or outdoor ones. Because of the substantial differences in object distribution and poin…