# Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding

arXiv: https://arxiv.org/abs/2608.29177 · HTML: https://mlsanity.com/paper/2608.29177/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 48 of its 55 references that are in the map.
- First posted on arXiv 29 Aug 2026.

## Builds on (most cited first, 30 of 48)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes](https://mlsanity.com/paper/1702.04405/) (2017)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [LRM: Large Reconstruction Model for Single Image to 3D](https://mlsanity.com/paper/2311.04400/) (2023)
- [MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo](https://mlsanity.com/paper/2103.15595/) (2021)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [IBRNet: Learning Multi-View Image-Based Rendering](https://mlsanity.com/paper/2102.13090/) (2021)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [LERF: Language Embedded Radiance Fields](https://mlsanity.com/paper/2303.09553/) (2023)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [Decomposing NeRF for Editing via Feature Field Distillation](https://mlsanity.com/paper/2205.15585/) (2022)
- [Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields](https://mlsanity.com/paper/2312.03203/) (2023)
- [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [Mask3D: Mask Transformer for 3D Semantic Instance Segmentation](https://mlsanity.com/paper/2210.03105/) (2022)
- [No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images](https://mlsanity.com/paper/2410.24207/) (2024)
- [MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos](https://mlsanity.com/paper/2412.04463/) (2024)
- [Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations](https://mlsanity.com/paper/2111.13152/) (2021)
- [LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias](https://mlsanity.com/paper/2410.17242/) (2024)
- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [WildGaussians: 3D Gaussian Splatting in the Wild](https://mlsanity.com/paper/2407.08447/) (2024)
- [Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats](https://mlsanity.com/paper/2410.12781/) (2024)
- [Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos](https://mlsanity.com/paper/2412.09621/) (2024)

## Abstract (arXiv)

The integration of novel view synthesis (NVS) and open-vocabulary segmentation (OVS) has recently yielded powerful feed-forward 3D foundation models. However, their inherent reliance on static-scene assumptions leads to severe misalignment of spatial features in unconstrained dynamic environments. To bridge this critical gap, we propose SPAR, a novel joint semantic-geometric encoding architecture that explicitly isolates transient dynamic noise prior to latent space aggregation. Furthermore, we introduce a dynamic-region-aware end-to-end training paradigm that structurally couples motion estimation with multi-view visual and semantic learning. This unified approach enables the network to inherently resolve motion conflicts and distill multi-view consistent, temporally stable scene representations from dynamic inputs. Extensive experiments on the challenging D-RE10K benchmark demonstrate that SPAR achieves state-of-the-art performance. Our end-to-end approach achieves exceptional novel view synthesis quality, yielding a PSNR of 22.15 dB and 23.33 dB given only 3 and 4 input views respectively. Despite being trained in a self-supervised manner, our model achieves an mIoU of 88.5% for motion mask prediction. Furthermore, our analysis reveals a strong inter-task synergy between photometric scene reconstruction and semantic understanding, where semantic synthesis learning consistently enhances photometric fidelity in novel view rendering. Code will be available at https://github.com/dmucby/SPAR.