Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction

• URL: http://arxiv.org/abs/2512.10267v1
• Date: Thu, 11 Dec 2025 04:10:21 GMT
• Title: Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction
• Authors: Chen Ziwen, Hao Tan, Peng Wang, Zexiang Xu, Li Fuxin,
• Abstract summary: Long-LRM++ is a model that adopts a semi-explicit scene representation combined with a lightweight decoder.<n>Long-LRM++ matches the rendering quality of LaCT on DL3DV while achieving real-time 14 FPS rendering on an A100 GPU.<n>Our design also scales to 64 input views at the $950times540$ resolution, demonstrating strong generalization to increased input lengths.
• Score: 19.234118544637592
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in generalizable Gaussian splatting (GS) have enabled feed-forward reconstruction of scenes from tens of input views. Long-LRM notably scales this paradigm to 32 input images at $950\times540$ resolution, achieving 360° scene-level reconstruction in a single forward pass. However, directly predicting millions of Gaussian parameters at once remains highly error-sensitive: small inaccuracies in positions or other attributes lead to noticeable blurring, particularly in fine structures such as text. In parallel, implicit representation methods such as LVSM and LaCT have demonstrated significantly higher rendering fidelity by compressing scene information into model weights rather than explicit Gaussians, and decoding RGB frames using the full transformer or TTT backbone. However, this computationally intensive decompression process for every rendered frame makes real-time rendering infeasible. These observations raise key questions: Is the deep, sequential "decompression" process necessary? Can we retain the benefits of implicit representations while enabling real-time performance? We address these questions with Long-LRM++, a model that adopts a semi-explicit scene representation combined with a lightweight decoder. Long-LRM++ matches the rendering quality of LaCT on DL3DV while achieving real-time 14 FPS rendering on an A100 GPU, overcoming the speed limitations of prior implicit methods. Our design also scales to 64 input views at the $950\times540$ resolution, demonstrating strong generalization to increased input lengths. Additionally, Long-LRM++ delivers superior novel-view depth prediction on ScanNetv2 compared to direct depth rendering from Gaussians. Extensive ablation studies validate the effectiveness of each component in the proposed framework.

Related papers

• LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering [75.67501939005119]
  We present a novel level-of-detail (LOD) method for 3D Gaussian Splatting on memory-constrained devices.<n>Our approach iteratively selects optimal subsets of Gaussians based on camera distance.<n>Our method achieves state-of-the-art performance on both outdoor (Hierarchical 3DGS) and indoor (Zip-NeRF) datasets.
  arXiv  Detail & Related papers  (2025-05-29T06:50:57Z)
• FlowR: Flowing from Sparse to Dense 3D Reconstructions [60.28571003356382]
  We propose a flow matching model that learns a flow to connect novel view renderings from possibly sparse reconstructions to renderings that we expect from dense reconstructions.<n>Our model is trained on a novel dataset of 3.6M image pairs and can process up to 45 views at 540x960 resolution (91K tokens) on one H100 GPU in a single forward pass.
  arXiv  Detail & Related papers  (2025-04-02T11:57:01Z)
• SparseGS-W: Sparse-View 3D Gaussian Splatting in the Wild with Generative Priors [22.561786156613525]
  We propose SparseGS-W, a novel framework to Synthesizing novel views of large-scale scenes from unconstrained in-the-wild images.<n>We leverage geometric priors and constrained diffusion priors to compensate for the lack of multi-view information from extremely sparse input.<n>SparseGS-W achieves state-of-the-art performance not only in full-reference metrics, but also in commonly used non-reference metrics such as FID, ClipIQA, and MUSIQ.
  arXiv  Detail & Related papers  (2025-03-25T08:40:40Z)
• STORM: Token-Efficient Long Video Understanding for Multimodal LLMs [116.4479155699528]
  STORM is a novel architecture incorporating a dedicated temporal encoder between the image encoder and the Video-LLMs.<n>We show that STORM achieves state-of-the-art results across various long video understanding benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T06:17:38Z)
• GPS-Gaussian+: Generalizable Pixel-wise 3D Gaussian Splatting for Real-Time Human-Scene Rendering from Sparse Views [67.34073368933814]
  We propose a generalizable Gaussian Splatting approach for high-resolution image rendering under a sparse-view camera setting. We train our Gaussian parameter regression module on human-only data or human-scene data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. Experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed.
  arXiv  Detail & Related papers  (2024-11-18T08:18:44Z)
• Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats [31.37432523412404]
  Long-LRM is a feed-forward 3D Gaussian reconstruction model for instant, high-resolution, 360deg wide-coverage, scene-level reconstruction.<n>It takes in 32 input images at a resolution of 960x540 and produces the reconstruction in just 1 second on a single A100 GPU.<n>We evaluate Long-LRM on the large-scale DL3DV benchmark and Tanks&Temples, demonstrating reconstruction quality comparable to the optimization-based methods.
  arXiv  Detail & Related papers  (2024-10-16T17:54:06Z)
• PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [59.277480452459315]
  We propose a principled sensitivity pruning score that preserves visual fidelity and foreground details at significantly higher compression ratios.<n>We also propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing its training pipeline.
  arXiv  Detail & Related papers  (2024-06-14T17:53:55Z)
• EndoGaussian: Real-time Gaussian Splatting for Dynamic Endoscopic Scene Reconstruction [36.35631592019182]
  We introduce EndoGaussian, a real-time endoscopic scene reconstruction framework built on 3D Gaussian Splatting (3DGS) Our framework significantly boosts the rendering speed to a real-time level. Experiments on public datasets demonstrate our efficacy against prior SOTAs in many aspects.
  arXiv  Detail & Related papers  (2024-01-23T08:44:26Z)
• LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS [55.85673901231235]
  We introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework.
  arXiv  Detail & Related papers  (2023-11-28T21:39:20Z)
• Scalable Neural Video Representations with Learnable Positional Features [73.51591757726493]
  We show how to train neural representations with learnable positional features (NVP) that effectively amortize a video as latent codes. We demonstrate the superiority of NVP on the popular UVG benchmark; compared with prior arts, NVP not only trains 2 times faster (less than 5 minutes) but also exceeds their encoding quality as 34.07rightarrow$34.57 (measured with the PSNR metric)
  arXiv  Detail & Related papers  (2022-10-13T08:15:08Z)

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.