InstantHDR: Single-forward Gaussian Splatting for High Dynamic Range 3D Reconstruction

• URL: http://arxiv.org/abs/2603.11298v2
• Date: Tue, 17 Mar 2026 18:53:02 GMT
• Title: InstantHDR: Single-forward Gaussian Splatting for High Dynamic Range 3D Reconstruction
• Abstract summary: Existing HDR pipelines rely on known camera poses, well-calibrated dense point clouds, and time-consuming per-scene optimization.<n>Current feed-forward alternatives overlook the HDR problem by assuming exposure-in appearance.<n>We propose Instant, a feed-forward network that reconstructs 3D HDR scenes from uncalibrated multi-exposure LDR collections in a single forward pass.
• Score: 48.64335106961342
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: High dynamic range (HDR) novel view synthesis (NVS) aims to reconstruct HDR scenes from multi-exposure low dynamic range (LDR) images. Existing HDR pipelines heavily rely on known camera poses, well-initialized dense point clouds, and time-consuming per-scene optimization. Current feed-forward alternatives overlook the HDR problem by assuming exposure-invariant appearance. To bridge this gap, we propose InstantHDR, a feed-forward network that reconstructs 3D HDR scenes from uncalibrated multi-exposure LDR collections in a single forward pass. Specifically, we design a geometry-guided appearance modeling for multi-exposure fusion, and a meta-network for generalizable scene-specific tone mapping. Due to the lack of HDR scene data, we build a pre-training dataset, called HDR-Pretrain, for generalizable feed-forward HDR models, featuring 168 Blender-rendered scenes, diverse lighting types, and multiple camera response functions. Comprehensive experiments show that our InstantHDR delivers comparable synthesis performance to the state-of-the-art optimization-based HDR methods while enjoying $\sim700\times$ and $\sim20\times$ reconstruction speed improvement with our single-forward and post-optimization settings. All code, models, and datasets will be released after the review process.

Related papers

• Reconstructing 3D Scenes in Native High Dynamic Range [82.90064638813185]
  We present the first method for 3D scene reconstruction that directly models native HDR observations.<n>We propose bf Native High dynamic range 3D Gaussian Splatting (NH-3DGS), which preserves the full dynamic range throughout the reconstruction pipeline.<n>We demonstrate on both synthetic and real multi-view HDR datasets that NH-3DGS significantly outperforms existing methods in reconstruction quality and dynamic range preservation.
  arXiv  Detail & Related papers  (2025-11-17T02:33:31Z)
• Diffusion-Promoted HDR Video Reconstruction [45.73396977607666]
  High dynamic range (LDR) video reconstruction aims to generate HDR videos from low dynamic range (LDR) frames captured with alternating exposures. Most existing works solely rely on the regression-based paradigm, leading to adverse effects such as ghosting artifacts and missing details in saturated regions. We propose a diffusion-promoted method for HDR video reconstruction, termed HDR-V-Diff, which incorporates a diffusion model to capture the HDR distribution.
  arXiv  Detail & Related papers  (2024-06-12T13:38:10Z)
• 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)
• 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)
• GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild [74.52723408793648]
  We present the first method for learning a generative model of HDR images from in-the-wild LDR image collections in a fully unsupervised manner. The key idea is to train a generative adversarial network (GAN) to generate HDR images which, when projected to LDR under various exposures, are indistinguishable from real LDR images. Experiments show that our method GlowGAN can synthesize photorealistic HDR images in many challenging cases such as landscapes, lightning, or windows.
  arXiv  Detail & Related papers  (2022-11-22T15:42:08Z)
• Self-supervised HDR Imaging from Motion and Exposure Cues [14.57046548797279]
  We propose a novel self-supervised approach for learnable HDR estimation that alleviates the need for HDR ground-truth labels. Experimental results show that the HDR models trained using our proposed self-supervision approach achieve performance competitive with those trained under full supervision.
  arXiv  Detail & Related papers  (2022-03-23T10:22:03Z)
• 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)
• HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions [62.44802076971331]
  We propose a novel GAN-based model, HDR-GAN, for synthesizing HDR images from multi-exposed LDR images. By incorporating adversarial learning, our method is able to produce faithful information in the regions with missing content.
  arXiv  Detail & Related papers  (2020-07-03T11:42:35Z)

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.