# SSCNav: Confidence-Aware Semantic Scene Completion for Visual Semantic Navigation

arXiv: https://arxiv.org/abs/2012.04512 · HTML: https://mlsanity.com/paper/2012.04512/

## Key facts

- Cited by 43 papers in the map (data through 7 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 30 of 43)

- [CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation](https://mlsanity.com/paper/2203.10421/) (2022)
- [ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings](https://mlsanity.com/paper/2206.12403/) (2022)
- [PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning](https://mlsanity.com/paper/2201.10029/) (2022)
- [Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models](https://mlsanity.com/paper/2207.11514/) (2022)
- [Cross-modal Map Learning for Vision and Language Navigation](https://mlsanity.com/paper/2203.05137/) (2022)
- [PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav](https://mlsanity.com/paper/2301.07302/) (2023)
- [Auxiliary Tasks and Exploration Enable ObjectNav](https://mlsanity.com/paper/2104.04112/) (2021)
- [How To Not Train Your Dragon: Training-free Embodied Object Goal Navigation with Semantic Frontiers](https://mlsanity.com/paper/2305.16925/) (2023)
- [Learning to Map for Active Semantic Goal Navigation](https://mlsanity.com/paper/2106.15648/) (2021)
- [Uncertainty-driven Planner for Exploration and Navigation](https://mlsanity.com/paper/2202.11907/) (2022)
- [PEANUT: Predicting and Navigating to Unseen Targets](https://mlsanity.com/paper/2212.02497/) (2022)
- [Learning Active Camera for Multi-Object Navigation](https://mlsanity.com/paper/2210.07505/) (2022)
- [Search for or Navigate to? Dual Adaptive Thinking for Object Navigation](https://mlsanity.com/paper/2208.00553/) (2022)
- [Navigating to Objects in Unseen Environments by Distance Prediction](https://mlsanity.com/paper/2202.03735/) (2022)
- [ViHOPE: Visuotactile In-Hand Object 6D Pose Estimation with Shape Completion](https://mlsanity.com/paper/2309.05662/) (2023)
- [Cross-Modality Time-Variant Relation Learning for Generating Dynamic Scene Graphs](https://mlsanity.com/paper/2305.08522/) (2023)
- [CasFusionNet: A Cascaded Network for Point Cloud Semantic Scene Completion by Dense Feature Fusion](https://mlsanity.com/paper/2211.13702/) (2022)
- [Multi-Agent Embodied Visual Semantic Navigation with Scene Prior Knowledge](https://mlsanity.com/paper/2109.09531/) (2021)
- [Agent-Centric Relation Graph for Object Visual Navigation](https://mlsanity.com/paper/2111.14422/) (2021)
- [Language-Conditioned Path Planning](https://mlsanity.com/paper/2308.16893/) (2023)
- [Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation](https://mlsanity.com/paper/2302.01520/) (2023)
- [Co-NavGPT: Multi-Robot Cooperative Visual Semantic Navigation Using Vision Language Models](https://mlsanity.com/paper/2310.07937/) (2023)
- [Aligning Knowledge Graph with Visual Perception for Object-goal Navigation](https://mlsanity.com/paper/2402.18892/) (2024)
- [Scene Editing as Teleoperation: A Case Study in 6DoF Kit Assembly](https://mlsanity.com/paper/2110.04450/) (2021)
- [E(2)-Equivariant Graph Planning for Navigation](https://mlsanity.com/paper/2309.13043/) (2023)
- [NavQ: Learning a Q-Model for Foresighted Vision-and-Language Navigation](https://mlsanity.com/paper/2510.16457/) (2025)
- [CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion](https://mlsanity.com/paper/2307.07938/) (2023)
- [Cognitive Planning for Object Goal Navigation using Generative AI Models](https://mlsanity.com/paper/2404.00318/) (2024)
- [Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidance](https://mlsanity.com/paper/2308.12845/) (2023)
- [4CNet: A Diffusion Approach to Map Prediction for Decentralized Multi-Robot Exploration](https://mlsanity.com/paper/2402.17904/) (2024)

## Abstract (arXiv)

This paper focuses on visual semantic navigation, the task of producing actions for an active agent to navigate to a specified target object category in an unknown environment. To complete this task, the algorithm should simultaneously locate and navigate to an instance of the category. In comparison to the traditional point goal navigation, this task requires the agent to have a stronger contextual prior to indoor environments. We introduce SSCNav, an algorithm that explicitly models scene priors using a confidence-aware semantic scene completion module to complete the scene and guide the agent's navigation planning. Given a partial observation of the environment, SSCNav first infers a complete scene representation with semantic labels for the unobserved scene together with a confidence map associated with its own prediction. Then, a policy network infers the action from the scene completion result and confidence map. Our experiments demonstrate that the proposed scene completion module improves the efficiency of the downstream navigation policies. Video, code, and data: https://sscnav.cs.columbia.edu/