# VisHall3D: Monocular Semantic Scene Completion from Reconstructing the Visible Regions to Hallucinating the Invisible Regions

arXiv: https://arxiv.org/abs/2507.19188 · HTML: https://mlsanity.com/paper/2507.19188/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 49 references that are in the map.
- First posted on arXiv 25 Jul 2025.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D](https://mlsanity.com/paper/2008.05711/) (2020)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Sparse R-CNN: End-to-End Object Detection with Learnable Proposals](https://mlsanity.com/paper/2011.12450/) (2020)
- [Semantic Scene Completion from a Single Depth Image](https://mlsanity.com/paper/1611.08974/) (2016)
- [Cascade R-CNN: High Quality Object Detection and Instance Segmentation](https://mlsanity.com/paper/1906.09756/) (2019)
- [Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2302.07817/) (2023)
- [MonoScene: Monocular 3D Semantic Scene Completion](https://mlsanity.com/paper/2112.00726/) (2021)
- [Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation](https://mlsanity.com/paper/2206.02777/) (2022)
- [SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving](https://mlsanity.com/paper/2303.09551/) (2023)
- [VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.12251/) (2023)
- [OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction](https://mlsanity.com/paper/2304.05316/) (2023)
- [Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion](https://mlsanity.com/paper/2012.03762/) (2020)
- [LMSCNet: Lightweight Multiscale 3D Semantic Completion](https://mlsanity.com/paper/2008.10559/) (2020)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)
- [FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation](https://mlsanity.com/paper/2307.01492/) (2023)
- [Anisotropic Convolutional Networks for 3D Semantic Scene Completion](https://mlsanity.com/paper/2004.02122/) (2020)
- [S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds](https://mlsanity.com/paper/2012.09242/) (2020)
- [Symphonize 3D Semantic Scene Completion with Contextual Instance Queries](https://mlsanity.com/paper/2306.15670/) (2023)
- [NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space](https://mlsanity.com/paper/2309.14616/) (2023)
- [AutoShape: Real-Time Shape-Aware Monocular 3D Object Detection](https://mlsanity.com/paper/2108.11127/) (2021)
- [MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection](https://mlsanity.com/paper/2203.13310/) (2022)
- [OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion](https://mlsanity.com/paper/2302.13540/) (2023)

## Built on by (most cited first, 7 of 7)

- [OneOcc: Semantic Occupancy Prediction for Legged Robots with a Single Panoramic Camera](https://mlsanity.com/paper/2511.03571/) (2025)
- [VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion](https://mlsanity.com/paper/2512.18954/) (2025)
- [Adaptive Multi-Scale Channel-Spatial Attention Aggregation Framework for 3D Indoor Semantic Scene Completion Toward Assisting Visually Impaired](https://mlsanity.com/paper/2602.16385/) (2026)
- [Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion](https://mlsanity.com/paper/2604.05780/) (2026)
- [Semantic Occupancy Prediction with Dual Range-Voxel Representation](https://mlsanity.com/paper/2606.31688/) (2026)
- [Geometry-Aware Spatio-Temporal Context Modeling for 4D Occupancy Forecasting](https://mlsanity.com/paper/2608.15279/) (2026)
- [SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completion](https://mlsanity.com/paper/2609.17413/) (2026)

## Abstract (arXiv)

This paper introduces VisHall3D, a novel two-stage framework for monocular semantic scene completion that aims to address the issues of feature entanglement and geometric inconsistency prevalent in existing methods. VisHall3D decomposes the scene completion task into two stages: reconstructing the visible regions (vision) and inferring the invisible regions (hallucination). In the first stage, VisFrontierNet, a visibility-aware projection module, is introduced to accurately trace the visual frontier while preserving fine-grained details. In the second stage, OcclusionMAE, a hallucination network, is employed to generate plausible geometries for the invisible regions using a noise injection mechanism. By decoupling scene completion into these two distinct stages, VisHall3D effectively mitigates feature entanglement and geometric inconsistency, leading to significantly improved reconstruction quality. The effectiveness of VisHall3D is validated through extensive experiments on two challenging benchmarks: SemanticKITTI and SSCBench-KITTI-360. VisHall3D achieves state-of-the-art performance, outperforming previous methods by a significant margin and paves the way for more accurate and reliable scene understanding in autonomous driving and other applications.