161 citations · 387 across the 61 of their papers we have counts for
21 papers · 1 filter
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
Tai Wang, Xiaohan Mao, Chenming Zhu +11
In the realm of computer vision and robotics, embodied agents are expected to explore their environment and carry out human instructions. This necessitates the ability to fully und…
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…
Drag-A-Video: Non-rigid Video Editing with Point-based Interaction
Yao Teng, Enze Xie, Yue Wu +3
Video editing is a challenging task that requires manipulating videos on both the spatial and temporal dimensions. Existing methods for video editing mainly focus on changing the a…
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…
EgoPlan-Bench: Benchmarking Multimodal Large Language Models for Human-Level Planning
Yi Chen, Yuying Ge, Yixiao Ge +6
The pursuit of artificial general intelligence (AGI) has been accelerated by Multimodal Large Language Models (MLLMs), which exhibit superior reasoning, generalization capabilities…
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…
HumanGaussian: Text-Driven 3D Human Generation with Gaussian Splatting
Xian Liu, Xiaohang Zhan, Jiaxiang Tang +5
Realistic 3D human generation from text prompts is a desirable yet challenging task. Existing methods optimize 3D representations like mesh or neural fields via score distillation…
OV-PARTS: Towards Open-Vocabulary Part Segmentation
Meng Wei, Xiaoyu Yue, Wenwei Zhang +3
Segmenting and recognizing diverse object parts is a crucial ability in applications spanning various computer vision and robotic tasks. While significant progress has been made in…
HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion
Xian Liu, Jian Ren, Aliaksandr Siarohin +6
Despite significant advances in large-scale text-to-image models, achieving hyper-realistic human image generation remains a desirable yet unsolved task. Existing models like Stabl…
Understanding Masked Autoencoders From a Local Contrastive Perspective
Xiaoyu Yue, Lei Bai, Meng Wei +4
Masked AutoEncoder (MAE) has revolutionized the field of self-supervised learning with its simple yet effective masking and reconstruction strategies. However, despite achieving st…
Object2Scene: Putting Objects in Context for Open-Vocabulary 3D Detection
Chenming Zhu, Wenwei Zhang, Tai Wang +2
Point cloud-based open-vocabulary 3D object detection aims to detect 3D categories that do not have ground-truth annotations in the training set. It is extremely challenging becaus…
Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training
Xiaoyang Wu, Zhuotao Tian, Xin Wen +4
The rapid advancement of deep learning models often attributes to their ability to leverage massive training data. In contrast, such privilege has not yet fully benefited 3D deep l…
T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation
Kaiyi Huang, Chengqi Duan, Kaiyue Sun +3
Despite the impressive advances in text-to-image models, they often struggle to effectively compose complex scenes with multiple objects, displaying various attributes and relation…
UniG3D: A Unified 3D Object Generation Dataset
Qinghong Sun, Yangguang Li, ZeXiang Liu +5
The field of generative AI has a transformative impact on various areas, including virtual reality, autonomous driving, the metaverse, gaming, and robotics. Among these application…
SAM3D: Segment Anything in 3D Scenes
Yunhan Yang, Xiaoyang Wu, Tong He +2
In this work, we propose SAM3D, a novel framework that is able to predict masks in 3D point clouds by leveraging the Segment-Anything Model (SAM) in RGB images without further trai…
TVTSv2: Learning Out-of-the-box Spatiotemporal Visual Representations at Scale
Ziyun Zeng, Yixiao Ge, Zhan Tong +3
The ultimate goal for foundation models is realizing task-agnostic, i.e., supporting out-of-the-box usage without task-specific fine-tuning. Although breakthroughs have been made i…
Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation
Zeyu Lu, Chengyue Wu, Xinyuan Chen +4
Diffusion models have attained impressive visual quality for image synthesis. However, how to interpret and manipulate the latent space of diffusion models has not been extensively…
RIFormer: Keep Your Vision Backbone Effective While Removing Token Mixer
Jiahao Wang, Songyang Zhang, Yong Liu +6
This paper studies how to keep a vision backbone effective while removing token mixers in its basic building blocks. Token mixers, as self-attention for vision transformers (ViTs),…
Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images
Zeyu Lu, Di Huang, Lei Bai +4
Photos serve as a way for humans to record what they experience in their daily lives, and they are often regarded as trustworthy sources of information. However, there is a growing…
Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning
Xiaoyang Wu, Xin Wen, Xihui Liu +1
As a pioneering work, PointContrast conducts unsupervised 3D representation learning via leveraging contrastive learning over raw RGB-D frames and proves its effectiveness on vario…
DDP: Diffusion Model for Dense Visual Prediction
Yuanfeng Ji, Zhe Chen, Enze Xie +6
We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. Our approach follows a "noise-to-map" generative pa…