Appearance Decomposition Gaussian Splatting for Multi-Traversal Reconstruction

• URL: http://arxiv.org/abs/2604.05908v1
• Date: Tue, 07 Apr 2026 14:11:54 GMT
• Title: Appearance Decomposition Gaussian Splatting for Multi-Traversal Reconstruction
• Abstract summary: Multi-traversal scene reconstruction is important for high-fidelity autonomous driving simulation and digital twin construction.<n>This paper presents ADM-GS (Appearance Decomposition Splatting for Multi-Traversal Reconstruction), a framework that applies an explicit appearance decomposition to the static background.<n>In multi-traversal experiments, our method achieves a +0.98 dBR improvement over existing latent-based baselines.
• Score: 18.874270345504716
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-traversal scene reconstruction is important for high-fidelity autonomous driving simulation and digital twin construction. This task involves integrating multiple sequences captured from the same geographical area at different times. In this context, a primary challenge is the significant appearance inconsistency across traversals caused by varying illumination and environmental conditions, despite the shared underlying geometry. This paper presents ADM-GS (Appearance Decomposition Gaussian Splatting for Multi-Traversal Reconstruction), a framework that applies an explicit appearance decomposition to the static background to alleviate appearance entanglement across traversals. For the static background, we decompose the appearance into traversal-invariant material, representing intrinsic material properties, and traversal-dependent illumination, capturing lighting variations. Specifically, we propose a neural light field that utilizes a frequency-separated hybrid encoding strategy. By incorporating surface normals and explicit reflection vectors, this design separately captures low-frequency diffuse illumination and high-frequency specular reflections. Quantitative evaluations on the Argoverse 2 and Waymo Open datasets demonstrate the effectiveness of ADM-GS. In multi-traversal experiments, our method achieves a +0.98 dB PSNR improvement over existing latent-based baselines while producing more consistent appearance across traversals. Code will be available at https://github.com/IRMVLab/ADM-GS.

Related papers

• TransmissiveGS: Residual-Guided Disentangled Gaussian Splatting for Transmissive Scene Reconstruction and Rendering [25.24244829648333]
  We present TransmissiveGS, a novel framework for disentangled reconstruction and rendering of transmissive scenes.<n>Specifically, we model the scene with a dual-Gaussian representation and introduce a deferred shading function to jointly render the two Gaussian components.<n>We propose a reflection light field that enables high-fidelity estimation of near-field reflections.
  arXiv  Detail & Related papers  (2026-05-11T15:19:04Z)
• RT-GS: Gaussian Splatting with Reflection and Transmittance Primitives [52.10688811929143]
  We propose a unified framework that integrates a microfacet material model and ray tracing to jointly model specular reflection and transmittance in Gaussian Splatting.<n>Our experiments demonstrate that our method successfully produces reflections and recovers objects behind transparent surfaces in complex environments.
  arXiv  Detail & Related papers  (2026-04-01T05:50:03Z)
• Ref-DGS: Reflective Dual Gaussian Splatting [51.77181103979343]
  Reflective appearance, especially strong and typically near-field specular reflections, poses a fundamental challenge for accurate surface reconstruction and novel view.<n>We present Ref-DGS, a reflective dual Gaussian splatting framework that addresses this trade-off.<n>Experiments demonstrate that Ref-DGS achieves state-of-the-art performance on reflective scenes while training substantially faster than ray-based Gaussian methods.
  arXiv  Detail & Related papers  (2026-03-08T14:54:15Z)
• GAINS: Gaussian-based Inverse Rendering from Sparse Multi-View Captures [23.677487511754006]
  We introduce GAINS (Gaussian-based Inverse rendering from Sparse multi-view captures)<n>It is a two-stage inverse rendering framework that leverages learning-based priors to stabilize geometry and material estimation.<n>It significantly improves material parameter accuracy, relighting quality, and novel-view synthesis compared to state-of-the-art inverse rendering methods.
  arXiv  Detail & Related papers  (2025-12-10T18:58:11Z)
• MaterialRefGS: Reflective Gaussian Splatting with Multi-view Consistent Material Inference [83.38607296779423]
  We show that multi-view consistent material inference with more physically-based environment modeling is key to learning accurate reflections with Gaussian Splatting.<n>Our method faithfully recovers both illumination and geometry, achieving state-of-the-art rendering quality in novel views synthesis.
  arXiv  Detail & Related papers  (2025-10-13T13:29:20Z)
• HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis [59.25751939710903]
  We propose a novel deformable Gaussian splatting framework that addresses embodied view synthesis from long monocular RGB videos.<n>Our method leverages invertible Gaussian Splatting deformation networks to reconstruct large-scale, dynamic environments accurately.<n>Results highlight a practical and scalable solution for EVS in real-world scenarios.
  arXiv  Detail & Related papers  (2025-06-24T03:54:40Z)
• NeFII: Inverse Rendering for Reflectance Decomposition with Near-Field Indirect Illumination [48.42173911185454]
  Inverse rendering methods aim to estimate geometry, materials and illumination from multi-view RGB images. We propose an end-to-end inverse rendering pipeline that decomposes materials and illumination from multi-view images.
  arXiv  Detail & Related papers  (2023-03-29T12:05:19Z)
• Exploring Invariant Representation for Visible-Infrared Person Re-Identification [77.06940947765406]
  Cross-spectral person re-identification, which aims to associate identities to pedestrians across different spectra, faces a main challenge of the modality discrepancy. In this paper, we address the problem from both image-level and feature-level in an end-to-end hybrid learning framework named robust feature mining network (RFM) Experiment results on two standard cross-spectral person re-identification datasets, RegDB and SYSU-MM01, have demonstrated state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-02-02T05:24:50Z)

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.