75 citations · 305 across the 39 of their papers we have counts for
12 papers · 1 filter
SPVC: Structured and Panoptic Video Fixing for Cross-Dataset Driving Scene Rendering
Gen Li, Shu Han, Yun Xi Qiao +5
Driving scene reconstruction and rendering, especially with 3D Gaussian Splatting, has become an important component of autonomous driving simulation. However, rendered views often…
Gaussians on a Diet: High-Quality Memory-Bounded 3D Gaussian Splatting Training
Yangming Zhang, Jian Xu, Chaojian Li +7
3D Gaussian Splatting (3DGS) has revolutionized novel view synthesis with high-quality rendering through continuous aggregations of millions of 3D Gaussian primitives. However, it…
Early-Bird Diffusion: Investigating and Leveraging Timestep-Aware Early-Bird Tickets in Diffusion Models for Efficient Training
Lexington Whalen, Zhenbang Du, Haoran You +4
Training diffusion models (DMs) requires substantial computational resources due to multiple forward and backward passes across numerous timesteps, motivating research into efficie…
Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields
Yonggan Fu, Huaizhi Qu, Zhifan Ye +3
Recent breakthroughs in Neural Radiance Fields (NeRFs) have sparked significant demand for their integration into real-world 3D applications. However, the varied functionalities re…
MixRT: Mixed Neural Representations For Real-Time NeRF Rendering
Chaojian Li, Bichen Wu, Peter Vajda +1
Neural Radiance Field (NeRF) has emerged as a leading technique for novel view synthesis, owing to its impressive photorealistic reconstruction and rendering capability. Neverthele…
Instant-NeRF: Instant On-Device Neural Radiance Field Training via Algorithm-Accelerator Co-Designed Near-Memory Processing
Yang Zhao, Shang Wu, Jingqun Zhang +3
Instant on-device Neural Radiance Fields (NeRFs) are in growing demand for unleashing the promise of immersive AR/VR experiences, but are still limited by their prohibitive trainin…
INGeo: Accelerating Instant Neural Scene Reconstruction with Noisy Geometry Priors
Chaojian Li, Bichen Wu, Albert Pumarola +3
We present a method that accelerates reconstruction of 3D scenes and objects, aiming to enable instant reconstruction on edge devices such as mobile phones and AR/VR headsets. Whil…
ViTALiTy: Unifying Low-rank and Sparse Approximation for Vision Transformer Acceleration with a Linear Taylor Attention
Jyotikrishna Dass, Shang Wu, Huihong Shi +4
Vision Transformer (ViT) has emerged as a competitive alternative to convolutional neural networks for various computer vision applications. Specifically, ViT multi-head attention…
MIA-Former: Efficient and Robust Vision Transformers via Multi-grained Input-Adaptation
Zhongzhi Yu, Yonggan Fu, Sicheng Li +2
ViTs are often too computationally expensive to be fitted onto real-world resource-constrained devices, due to (1) their quadratically increased complexity with the number of input…
FBNetV5: Neural Architecture Search for Multiple Tasks in One Run
Bichen Wu, Chaojian Li, Hang Zhang +6
Neural Architecture Search (NAS) has been widely adopted to design accurate and efficient image classification models. However, applying NAS to a new computer vision task still req…
DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference
Chaojian Li, Wuyang Chen, Yuchen Gu +4
Semantic segmentation for scene understanding is nowadays widely demanded, raising significant challenges for the algorithm efficiency, especially its applications on resource-limi…
FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training
Yonggan Fu, Haoran You, Yang Zhao +5
Recent breakthroughs in deep neural networks (DNNs) have fueled a tremendous demand for intelligent edge devices featuring on-site learning, while the practical realization of such…