Zobrazeno 1 - 10
of 141
pro vyhledávání: '"Xu, Chenfeng"'
Autor:
Li, Yiheng, Ge, Chongjian, Li, Chenran, Xu, Chenfeng, Tomizuka, Masayoshi, Tang, Chen, Ding, Mingyu, Zhan, Wei
We propose Waymo Open Motion Dataset-Reasoning (WOMD-Reasoning), a language annotation dataset built on WOMD, with a focus on describing and reasoning interactions and intentions in driving scenarios. Previous language datasets primarily captured int
Externí odkaz:
http://arxiv.org/abs/2407.04281
Autor:
Wang, Yixiao, Zhang, Yifei, Huo, Mingxiao, Tian, Ran, Zhang, Xiang, Xie, Yichen, Xu, Chenfeng, Ji, Pengliang, Zhan, Wei, Ding, Mingyu, Tomizuka, Masayoshi
The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all tasks, facing challenges such as high computational costs and catastroph
Externí odkaz:
http://arxiv.org/abs/2407.01531
In this paper, we point out suboptimal noise-data mapping leads to slow training of diffusion models. During diffusion training, current methods diffuse each image across the entire noise space, resulting in a mixture of all images at every point in
Externí odkaz:
http://arxiv.org/abs/2406.12303
Generating realistic images from arbitrary views based on a single source image remains a significant challenge in computer vision, with broad applications ranging from e-commerce to immersive virtual experiences. Recent advancements in diffusion mod
Externí odkaz:
http://arxiv.org/abs/2405.18677
Autor:
Liang, Feng, Kodaira, Akio, Xu, Chenfeng, Tomizuka, Masayoshi, Keutzer, Kurt, Marculescu, Diana
This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video (V2V) translation with user prompts. Unlike prior V2V methods using batches to process limited frames, we opt to process frames in a streaming fashion
Externí odkaz:
http://arxiv.org/abs/2405.15757
Autor:
Wang, Guangming, Pan, Lei, Peng, Songyou, Liu, Shaohui, Xu, Chenfeng, Miao, Yanzi, Zhan, Wei, Tomizuka, Masayoshi, Pollefeys, Marc, Wang, Hesheng
Meticulous 3D environment representations have been a longstanding goal in computer vision and robotics fields. The recent emergence of neural implicit representations has introduced radical innovation to this field as implicit representations enable
Externí odkaz:
http://arxiv.org/abs/2405.01333
Autor:
Peng, Chensheng, Xu, Chenfeng, Wang, Yue, Ding, Mingyu, Yang, Heng, Tomizuka, Masayoshi, Keutzer, Kurt, Pavone, Marco, Zhan, Wei
Monocular SLAM has long grappled with the challenge of accurately modeling 3D geometries. Recent advances in Neural Radiance Fields (NeRF)-based monocular SLAM have shown promise, yet these methods typically focus on novel view synthesis rather than
Externí odkaz:
http://arxiv.org/abs/2403.08125
Autor:
Chen, Lawrence Yunliang, Hari, Kush, Dharmarajan, Karthik, Xu, Chenfeng, Vuong, Quan, Goldberg, Ken
The ability to reuse collected data and transfer trained policies between robots could alleviate the burden of additional data collection and training. While existing approaches such as pretraining plus finetuning and co-training show promise, they d
Externí odkaz:
http://arxiv.org/abs/2402.19249
Autor:
Kodaira, Akio, Xu, Chenfeng, Hazama, Toshiki, Yoshimoto, Takanori, Ohno, Kohei, Mitsuhori, Shogo, Sugano, Soichi, Cho, Hanying, Liu, Zhijian, Keutzer, Kurt
We introduce StreamDiffusion, a real-time diffusion pipeline designed for interactive image generation. Existing diffusion models are adept at creating images from text or image prompts, yet they often fall short in real-time interaction. This limita
Externí odkaz:
http://arxiv.org/abs/2312.12491
We present 3DiffTection, a state-of-the-art method for 3D object detection from single images, leveraging features from a 3D-aware diffusion model. Annotating large-scale image data for 3D detection is resource-intensive and time-consuming. Recently,
Externí odkaz:
http://arxiv.org/abs/2311.04391