Zobrazeno 1 - 10
of 838
pro vyhledávání: '"Lu Jiwen"'
Autor:
Fei, Xin, Zheng, Wenzhao, Duan, Yueqi, Zhan, Wei, Tomizuka, Masayoshi, Keutzer, Kurt, Lu, Jiwen
We propose PixelGaussian, an efficient feed-forward framework for learning generalizable 3D Gaussian reconstruction from arbitrary views. Most existing methods rely on uniform pixel-wise Gaussian representations, which learn a fixed number of 3D Gaus
Externí odkaz:
http://arxiv.org/abs/2410.18979
Mamba has garnered widespread attention due to its flexible design and efficient hardware performance to process 1D sequences based on the state space model (SSM). Recent studies have attempted to apply Mamba to the visual domain by flattening 2D ima
Externí odkaz:
http://arxiv.org/abs/2410.10382
Vision mambas have demonstrated strong performance with linear complexity to the number of vision tokens. Their efficiency results from processing image tokens sequentially. However, most existing methods employ patch-based image tokenization and the
Externí odkaz:
http://arxiv.org/abs/2410.10316
In this paper, we propose a new framework for zero-shot object navigation. Existing zero-shot object navigation methods prompt LLM with the text of spatially closed objects, which lacks enough scene context for in-depth reasoning. To better preserve
Externí odkaz:
http://arxiv.org/abs/2410.08189
In this paper, we propose a post-training quantization framework of large vision-language models (LVLMs) for efficient multi-modal inference. Conventional quantization methods sequentially search the layer-wise rounding functions by minimizing activa
Externí odkaz:
http://arxiv.org/abs/2410.08119
In this paper, we propose a One-Point-One NeRF (OPONeRF) framework for robust scene rendering. Existing NeRFs are designed based on a key assumption that the target scene remains unchanged between the training and test time. However, small but unpred
Externí odkaz:
http://arxiv.org/abs/2409.20043
Building on the success of diffusion models in visual generation, flow-based models reemerge as another prominent family of generative models that have achieved competitive or better performance in terms of both visual quality and inference speed. By
Externí odkaz:
http://arxiv.org/abs/2409.18128
Visual data comes in various forms, ranging from small icons of just a few pixels to long videos spanning hours. Existing multi-modal LLMs usually standardize these diverse visual inputs to a fixed resolution for visual encoders and yield similar num
Externí odkaz:
http://arxiv.org/abs/2409.12961
Diffusion probabilistic models (DPMs) have shown remarkable performance in visual synthesis but are computationally expensive due to the need for multiple evaluations during the sampling. Recent predictor-corrector diffusion samplers have significant
Externí odkaz:
http://arxiv.org/abs/2409.03755
Embodied tasks require the agent to fully understand 3D scenes simultaneously with its exploration, so an online, real-time, fine-grained and highly-generalized 3D perception model is desperately needed. Since high-quality 3D data is limited, directl
Externí odkaz:
http://arxiv.org/abs/2408.11811