HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction from Raw Images

• URL: http://arxiv.org/abs/2407.16503v1
• Date: Tue, 23 Jul 2024 14:21:00 GMT
• Title: HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction from Raw Images
• Authors: Shreyas Singh, Aryan Garg, Kaushik Mitra,
• Abstract summary: 3D Gaussian Splatting (3DGS) has revolutionized the 3D scene reconstruction space enabling high-fidelity novel view in real-time. However, prior 3DGS and NeRF-based methods rely on 8-bit tone-mapped Low Dynamic Range images for scene reconstruction. Our proposed method HDRSplat tailors 3DGS to train directly on 14-bit linear raw images in near darkness which preserves the scenes' full dynamic range and content.
• Score: 14.332077246864628
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The recent advent of 3D Gaussian Splatting (3DGS) has revolutionized the 3D scene reconstruction space enabling high-fidelity novel view synthesis in real-time. However, with the exception of RawNeRF, all prior 3DGS and NeRF-based methods rely on 8-bit tone-mapped Low Dynamic Range (LDR) images for scene reconstruction. Such methods struggle to achieve accurate reconstructions in scenes that require a higher dynamic range. Examples include scenes captured in nighttime or poorly lit indoor spaces having a low signal-to-noise ratio, as well as daylight scenes with shadow regions exhibiting extreme contrast. Our proposed method HDRSplat tailors 3DGS to train directly on 14-bit linear raw images in near darkness which preserves the scenes' full dynamic range and content. Our key contributions are two-fold: Firstly, we propose a linear HDR space-suited loss that effectively extracts scene information from noisy dark regions and nearly saturated bright regions simultaneously, while also handling view-dependent colors without increasing the degree of spherical harmonics. Secondly, through careful rasterization tuning, we implicitly overcome the heavy reliance and sensitivity of 3DGS on point cloud initialization. This is critical for accurate reconstruction in regions of low texture, high depth of field, and low illumination. HDRSplat is the fastest method to date that does 14-bit (HDR) 3D scene reconstruction in $\le$15 minutes/scene ($\sim$30x faster than prior state-of-the-art RawNeRF). It also boasts the fastest inference speed at $\ge$120fps. We further demonstrate the applicability of our HDR scene reconstruction by showcasing various applications like synthetic defocus, dense depth map extraction, and post-capture control of exposure, tone-mapping and view-point.

Related papers

• CasualHDRSplat: Robust High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos [15.52886867095313]
  Photo-realistic novel view rendering from multi-view images, such as neural radiance field (NeRF) and 3D Splatting (3DGS), have garnered widespread attention due to their superior performance. textbfSplat contains a unified differentiable physical imaging model which applies continuous-time trajectory constraint to imaging process. Experiments demonstrate that our approach outperforms existing methods in terms of robustness and quality.
  arXiv  Detail & Related papers  (2025-04-24T16:42:37Z)
• Beyond Gaussians: Fast and High-Fidelity 3D Splatting with Linear Kernels [51.08794269211701]
  We introduce 3D Linear Splatting (3DLS), which replaces Gaussian kernels with linear kernels to achieve sharper and more precise results. 3DLS demonstrates state-of-the-art fidelity and accuracy, along with a 30% FPS improvement over baseline 3DGS.
  arXiv  Detail & Related papers  (2024-11-19T11:59:54Z)
• EVER: Exact Volumetric Ellipsoid Rendering for Real-time View Synthesis [72.53316783628803]
  We present Exact Volumetric Ellipsoid Rendering (EVER), a method for real-time differentiable emission-only volume rendering. Unlike recentization based approach by 3D Gaussian Splatting (3DGS), our primitive based representation allows for exact volume rendering. We show that our method is more accurate with blending issues than 3DGS and follow-up work on view rendering.
  arXiv  Detail & Related papers  (2024-10-02T17:59:09Z)
• Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis [35.81034036380374]
  Volumetric rendering based methods excel in HDR view synthesis from RAWimages, especially for nighttime scenes. They suffer from long training times and cannot perform real-time rendering due to dense sampling requirements. The advent of 3D Gaussian Splatting (3DGS) enables real-time rendering and faster training. These designs enable LE3D to perform real-time novel view synthesis, HDR rendering, refocusing, and tone-mapping changes.
  arXiv  Detail & Related papers  (2024-06-10T12:33:08Z)
• HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting [76.5908492298286]
  Existing HDR NVS methods are mainly based on NeRF. They suffer from long training time and slow inference speed. We propose a new framework, High Dynamic Range Gaussian Splatting (-GS)
  arXiv  Detail & Related papers  (2024-05-24T00:46:58Z)
• Fast High Dynamic Range Radiance Fields for Dynamic Scenes [39.3304365600248]
  We propose a dynamic HDR NeRF framework, named HDR-HexPlane, which can learn 3D scenes from dynamic 2D images captured with various exposures. With the proposed model, high-quality novel-view images at any time point can be rendered with any desired exposure.
  arXiv  Detail & Related papers  (2024-01-11T17:15:16Z)
• Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes [58.66427721308464]
  Self is a self-supervised reconstruction method that only requires dynamic multi-exposure images during training. Self achieves superior results against the state-of-the-art self-supervised methods, and comparable performance to supervised ones.
  arXiv  Detail & Related papers  (2023-10-03T07:10:49Z)
• RawHDR: High Dynamic Range Image Reconstruction from a Single Raw Image [36.17182977927645]
  High dynamic range (RGB) images capture much more intensity levels than standard ones. Current methods predominantly generate HDR images from 8-bit low dynamic range (LDR) s images that have been degraded by the camera processing pipeline. Unlike existing methods, the core idea of this work is to incorporate more informative Raw sensor data to generate HDR images.
  arXiv  Detail & Related papers  (2023-09-05T07:58:21Z)
• Spatiotemporally Consistent HDR Indoor Lighting Estimation [66.26786775252592]
  We propose a physically-motivated deep learning framework to solve the indoor lighting estimation problem. Given a single LDR image with a depth map, our method predicts spatially consistent lighting at any given image position. Our framework achieves photorealistic lighting prediction with higher quality compared to state-of-the-art single-image or video-based methods.
  arXiv  Detail & Related papers  (2023-05-07T20:36:29Z)
• PDRF: Progressively Deblurring Radiance Field for Fast and Robust Scene Reconstruction from Blurry Images [75.87721926918874]
  We present Progressively Deblurring Radiance Field (PDRF) PDRF is a novel approach to efficiently reconstruct high quality radiance fields from blurry images. We show that PDRF is 15X faster than previous State-of-The-Art scene reconstruction methods.
  arXiv  Detail & Related papers  (2022-08-17T03:42:29Z)
• HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset [30.249052175655606]
  We introduce a coarse-to-fine deep learning framework for HDR video reconstruction. Firstly, we perform coarse alignment and pixel blending in the image space to estimate the coarse HDR video. Secondly, we conduct more sophisticated alignment and temporal fusion in the feature space of the coarse HDR video to produce better reconstruction.
  arXiv  Detail & Related papers  (2021-03-27T16:40:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.