pith. sign in

arxiv: 2602.04516 · v3 · pith:EMXXCNV5new · submitted 2026-02-04 · 💻 cs.RO

TACO: Temporal Consensus Optimization for Continual Neural Mapping

Xunlan Zhou , Hongrui Zhao , Negar Mehr This is my paper

Pith reviewed 2026-05-21 13:56 UTC · model grok-4.3

classification 💻 cs.RO
keywords continual neural mappingtemporal consensus optimizationreplay-free learningneural implicit representationsrobotic scene understandingdynamic environmentsmemory-efficient adaptation
0
0 comments X

The pith

TACO reformulates neural mapping as temporal consensus optimization to enable replay-free continual adaptation to changing scenes.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes TACO as a replay-free framework for continual neural implicit mapping in dynamic robotic environments. It treats past model snapshots as temporal neighbors and updates the current map by enforcing weighted consensus with those historical representations. This allows reliable past geometry to constrain the optimization while still permitting revisions to unreliable or outdated regions in response to new observations. A sympathetic reader would care because most existing mapping systems either assume static scenes or require storing and replaying historical data, which violates memory and computation limits in real-world robot deployment. If the central claim holds, robots could maintain accurate maps over time in evolving environments without accumulating storage costs.

Core claim

We reformulate mapping as a temporal consensus optimization problem, where we treat past model snapshots as temporal neighbors. Intuitively, our approach resembles a model consulting its own past knowledge. We update the current map by enforcing weighted consensus with historical representations. Our method allows reliable past geometry to constrain optimization while permitting unreliable or outdated regions to be revised in response to new observations.

What carries the argument

Temporal consensus optimization, in which past model snapshots act as temporal neighbors to provide weighted constraints during the current map update.

If this is right

  • Memory usage stays bounded because no historical observations are stored or replayed.
  • The system can adapt maps to environmental changes while retaining consistency in stable regions.
  • Performance exceeds other continual learning baselines in both simulated and real-world robotic tests.
  • Mapping remains feasible under the strict memory and computation limits of physical robot platforms.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The consensus mechanism could be applied to other continual representation learning tasks that need long-term consistency without data retention.
  • Weighting of past snapshots might be improved by adding explicit uncertainty estimates from the current observations.
  • The approach suggests a path toward lifelong mapping on resource-constrained platforms such as drones or mobile manipulators.

Load-bearing premise

Past model snapshots can reliably serve as temporal neighbors whose weighted consensus constrains current geometry while still permitting updates to unreliable or outdated regions.

What would settle it

An experiment in which enforcing consensus with past snapshots prevents accurate incorporation of large scene changes, producing lower reconstruction accuracy than replay-based baselines over long sequences.

Figures

Figures reproduced from arXiv: 2602.04516 by Hongrui Zhao, Negar Mehr, Xunlan Zhou.

Figure 1
Figure 1. Figure 1: Comparison of continual neural mapping under environment changes. The yellow stool was moved from A to B. Left: TACO (Temporal Consensus Optimization) revises outdated regions while preserving consistent geometry and yields an accurate and up-to-date map. Middle: Replay-based methods (e.g., Co-SLAM) preserve high-quality reconstructions overall, but their reliance on replayed past observations can lead to … view at source ↗
Figure 2
Figure 2. Figure 2: Quantitative results on eight Replica scenes under static settings. We report reconstruction accuracy and completeness [PITH_FULL_IMAGE:figures/full_fig_p006_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Qualitative reconstruction results on a representative Gibson scene. [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Additional hardware experiment with multiple sequential scene changes [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Quantitative Results on ScanNet distance while preserving high completion, precision@5cm, and F1@5cm, demonstrating that importance-weighted tem￾poral consensus preserves global geometry without revisiting past observations. Compared to explicit replay (CNM, KR) and knowledge distillation (UNIKD), TACO achieves a more favorable accuracy–completeness trade-off, reducing spurious geometry without sacrificing… view at source ↗
Figure 6
Figure 6. Figure 6: Visualization on ScanNet scene0000_00. completely recovers the table region highlighted in the figure. C. Results on Dynamic Simulated Scenes To evaluate continual neural mapping under environment changes, we construct dynamic datasets based on the Habitat Synthetic Scenes Dataset. Using Habitat-Sim, we generate simulated environments in which scene geometry is modified in a staged manner, allowing us to i… view at source ↗
Figure 7
Figure 7. Figure 7: Dynamic scene reconstruction under staged object motion. Our method adapts to scene changes without artifacts, whereas replay- and regularization-based methods produce ghosting and mesh tearing, respectively. We further observe that the choice of the masking threshold τ is coupled with the penalty parameter ρ, which controls the overall strength of temporal consensus. Larger values of ρ amplify the influen… view at source ↗
read the original abstract

Neural implicit mapping has emerged as a powerful paradigm for robotic navigation and scene understanding. However, real-world robotic deployment requires continual adaptation to changing environments under strict memory and computation constraints, which existing mapping systems fail to support. Most prior methods rely on replaying historical observations to preserve consistency and assume static scenes. As a result, they cannot adapt to continual learning in dynamic robotic settings. To address these challenges, we propose TACO (TemporAl Consensus Optimization), a replay-free framework for continual neural mapping. We reformulate mapping as a temporal consensus optimization problem, where we treat past model snapshots as temporal neighbors. Intuitively, our approach resembles a model consulting its own past knowledge. We update the current map by enforcing weighted consensus with historical representations. Our method allows reliable past geometry to constrain optimization while permitting unreliable or outdated regions to be revised in response to new observations. TACO achieves a balance between memory efficiency and adaptability without storing or replaying previous data. Through extensive simulated and real-world experiments, we show that TACO robustly adapts to scene changes, and consistently outperforms other continual learning baselines.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper proposes TACO, a replay-free continual learning framework for neural implicit mapping in dynamic robotic environments. It reformulates mapping as a temporal consensus optimization problem that treats historical model snapshots as temporal neighbors, enforcing weighted consensus to constrain reliable past geometry while allowing updates to unreliable or changed regions. The method claims to achieve memory efficiency without data replay or storage and to outperform existing continual learning baselines in both simulated and real-world experiments.

Significance. If the central mechanism holds, TACO would represent a meaningful advance in continual neural mapping by removing the memory and computational overhead of replay buffers, which is a practical bottleneck for long-term robotic deployment in non-static scenes. The approach could enable more scalable scene understanding under strict resource constraints, provided the selective weighting proves robust.

major comments (2)
  1. [§3.2] §3.2 (Temporal Consensus Optimization): The update rule relies on implicit reliability signals derived from the weighted consensus term to selectively relax constraints in changed regions. However, the manuscript does not provide an explicit change-detection mechanism or ablation isolating whether the weighting preserves static geometry versus globally averaging under accumulated mapping drift or large-scale scene alterations. This assumption is load-bearing for the replay-free adaptation claim.
  2. [§4] §4 (Experiments): The reported outperformance over baselines lacks detailed ablation on the consensus weighting hyper-parameters and their sensitivity to mapping error accumulation. Without these controls, it is difficult to attribute gains specifically to the temporal neighbor mechanism rather than other implementation choices.
minor comments (2)
  1. [Abstract] The abstract states that TACO 'consistently outperforms' baselines but does not preview any quantitative metrics or key equations; adding one representative result or the form of the consensus loss would improve clarity.
  2. [§3] Notation for historical snapshots and weighting functions should be introduced with a single consistent symbol table or equation reference to avoid ambiguity across sections.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their detailed and constructive feedback on our manuscript. We address each of the major comments point by point below, and indicate the revisions we intend to make in the updated version.

read point-by-point responses

  1. Referee: [§3.2] §3.2 (Temporal Consensus Optimization): The update rule relies on implicit reliability signals derived from the weighted consensus term to selectively relax constraints in changed regions. However, the manuscript does not provide an explicit change-detection mechanism or ablation isolating whether the weighting preserves static geometry versus globally averaging under accumulated mapping drift or large-scale scene alterations. This assumption is load-bearing for the replay-free adaptation claim.

    Authors: We appreciate the referee pointing out this critical aspect of our method. TACO is designed to operate without an explicit change-detection mechanism, relying instead on the weighted consensus optimization to implicitly identify reliable versus unreliable regions based on agreement with temporal neighbors. This approach avoids the need for additional detection modules or data storage, which aligns with our goal of memory-efficient continual mapping. To better substantiate this, we will expand the explanation in §3.2 with a more formal analysis of how the weighting scheme prevents global averaging under drift. Furthermore, we will include a new ablation study in §4 that specifically examines the preservation of static geometry in the presence of scene changes and accumulated errors. We believe these additions will clarify the load-bearing assumptions. revision: partial

  2. Referee: [§4] §4 (Experiments): The reported outperformance over baselines lacks detailed ablation on the consensus weighting hyper-parameters and their sensitivity to mapping error accumulation. Without these controls, it is difficult to attribute gains specifically to the temporal neighbor mechanism rather than other implementation choices.

    Authors: We agree with the referee that more comprehensive ablations on the hyper-parameters would strengthen the experimental section. In the revised manuscript, we will add detailed sensitivity analyses for the consensus weighting parameters, including their behavior under increasing mapping error accumulation. These new experiments will help isolate the contribution of the temporal neighbor mechanism and provide better controls for attributing the observed performance gains. revision: yes

Circularity Check

0 steps flagged

No significant circularity; consensus optimization is an independent objective

full rationale

The paper reformulates continual neural mapping as a temporal consensus optimization problem in which past model snapshots are treated as temporal neighbors to enforce weighted consensus. This formulation is introduced directly from the problem requirements (replay-free adaptation to dynamic scenes) rather than being defined in terms of its own fitted outputs or predictions. No equations or steps reduce by construction to self-citations, fitted parameters renamed as predictions, or ansatzes imported from prior author work. The central mechanism (selective weighting to preserve reliable geometry while allowing revision of outdated regions) is presented as a new optimization objective with independent content, supported by experiments rather than tautological redefinition. The derivation chain remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the domain assumption that historical model snapshots encode usable geometric constraints; no free parameters or invented entities are identifiable from the abstract alone.

axioms (1)
  • domain assumption Past model snapshots can be treated as temporal neighbors that provide reliable constraints on current geometry while allowing revision of unreliable regions.
    This premise underpins the weighted consensus update rule described in the abstract.

pith-pipeline@v0.9.0 · 5720 in / 1169 out tokens · 42232 ms · 2026-05-21T13:56:16.607295+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

58 extracted references · 58 canonical work pages · 4 internal anchors

  1. [1]

    Methods for incremental learning: a survey.International Journal of Data Mining & Knowledge Management Process, 3(4):119, 2013

    RR Ade and PR Deshmukh. Methods for incremental learning: a survey.International Journal of Data Mining & Knowledge Management Process, 3(4):119, 2013

    work page 2013

  2. [2]

    Expert gate: Lifelong learning with a network of experts

    Rahaf Aljundi, Punarjay Chakravarty, and Tinne Tuyte- laars. Expert gate: Lifelong learning with a network of experts. InProceedings of the IEEE conference on computer vision and pattern recognition, pages 3366– 3375, 2017

    work page 2017

  3. [3]

    Memory aware synapses: Learning what (not) to forget

    Rahaf Aljundi, Francesca Babiloni, Mohamed Elhoseiny, Marcus Rohrbach, and Tinne Tuytelaars. Memory aware synapses: Learning what (not) to forget. InProceedings of the European conference on computer vision (ECCV), pages 139–154, 2018

    work page 2018

  4. [4]

    Di-nerf: Distributed nerf for collaborative learning with relative pose refinement.IEEE Robotics and Automation Letters, 2024

    Mahboubeh Asadi, Kourosh Zareinia, and Sajad Saeedi. Di-nerf: Distributed nerf for collaborative learning with relative pose refinement.IEEE Robotics and Automation Letters, 2024

    work page 2024

  5. [5]

    Neural rgb-d surface reconstruction

    Dejan Azinovi ´c, Ricardo Martin-Brualla, Dan B Gold- man, Matthias Nießner, and Justus Thies. Neural rgb-d surface reconstruction. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 6290–6301, June 2022

    work page 2022

  6. [6]

    Clnerf: Continual learning meets nerf

    Zhipeng Cai and Matthias M ¨uller. Clnerf: Continual learning meets nerf. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 23185–23194, 2023

    work page 2023

  7. [7]

    Efficient Lifelong Learning with A-GEM

    Arslan Chaudhry, Marc’Aurelio Ranzato, Marcus Rohrbach, and Mohamed Elhoseiny. Efficient lifelong learning with a-gem.arXiv preprint arXiv:1812.00420, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  8. [8]

    Chang, Manolis Savva, Ma- ciej Halber, Thomas Funkhouser, and Matthias Nießner

    Angela Dai, Angel X. Chang, Manolis Savva, Ma- ciej Halber, Thomas Funkhouser, and Matthias Nießner. Scannet: Richly-annotated 3d reconstructions of indoor scenes. InProc. Computer Vision and Pattern Recogni- tion (CVPR), IEEE, 2017

    work page 2017

  9. [9]

    A continual learning survey: Defying forgetting in classification tasks.IEEE transactions on pattern analysis and machine intelligence, 44(7):3366– 3385, 2021

    Matthias De Lange, Rahaf Aljundi, Marc Masana, Sarah Parisot, Xu Jia, Ale ˇs Leonardis, Gregory Slabaugh, and Tinne Tuytelaars. A continual learning survey: Defying forgetting in classification tasks.IEEE transactions on pattern analysis and machine intelligence, 44(7):3366– 3385, 2021

    work page 2021

  10. [10]

    Macim: Multi-agent collaborative implicit mapping.IEEE Robotics and Automation Letters, 9(5): 4369–4376, 2024

    Yinan Deng, Yujie Tang, Yi Yang, Danwei Wang, and Yufeng Yue. Macim: Multi-agent collaborative implicit mapping.IEEE Robotics and Automation Letters, 9(5): 4369–4376, 2024

    work page 2024

  11. [11]

    Openmulti: Open-vocabulary instance-level multi-agent distributed implicit mapping

    Jianyu Dou, Yinan Deng, Jiahui Wang, Xingsi Tang, Yi Yang, and Yufeng Yue. Openmulti: Open-vocabulary instance-level multi-agent distributed implicit mapping. IEEE Robotics and Automation Letters, 2025

    work page 2025

  12. [12]

    Podnet: Pooled outputs distillation for small-tasks incremental learning

    Arthur Douillard, Matthieu Cord, Charles Ollion, Thomas Robert, and Eduardo Valle. Podnet: Pooled outputs distillation for small-tasks incremental learning. InEuropean Conference on Computer Vision, pages 86–

    work page

  13. [13]

    PathNet: Evolution Channels Gradient Descent in Super Neural Networks

    Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A Rusu, Alexander Pritzel, and Daan Wierstra. Pathnet: Evolution channels gradi- ent descent in super neural networks.arXiv preprint arXiv:1701.08734, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  14. [14]

    Bayes’ rays: Uncertainty quan- tification for neural radiance fields

    Lily Goli, Cody Reading, Silvia Sell ´an, Alec Jacobson, and Andrea Tagliasacchi. Bayes’ rays: Uncertainty quan- tification for neural radiance fields. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 20061–20070, 2024

    work page 2024

  15. [15]

    Unikd: Uncertainty-filtered incremental knowledge distillation for neural implicit representation

    Mengqi Guo, Chen Li, Hanlin Chen, and Gim Hee Lee. Unikd: Uncertainty-filtered incremental knowledge distillation for neural implicit representation. InEuro- pean Conference on Computer Vision, pages 237–254. Springer, 2024

    work page 2024

  16. [16]

    Class- incremental learning by knowledge distillation with adaptive feature consolidation

    Minsoo Kang, Jaeyoo Park, and Bohyung Han. Class- incremental learning by knowledge distillation with adaptive feature consolidation. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16071–16080, 2022

    work page 2022

  17. [17]

    Habitat synthetic scenes dataset (hssd-200): An analysis of 3d scene scale and realism tradeoffs for objectgoal navigation

    Mukul Khanna, Yongsen Mao, Hanxiao Jiang, San- jay Haresh, Brennan Shacklett, Dhruv Batra, Alexander Clegg, Eric Undersander, Angel X Chang, and Manolis Savva. Habitat synthetic scenes dataset (hssd-200): An analysis of 3d scene scale and realism tradeoffs for objectgoal navigation. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern R...

    work page 2024

  18. [18]

    Overcoming catastrophic for- getting in neural networks.Proceedings of the national academy of sciences, 114(13):3521–3526, 2017

    James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, et al. Overcoming catastrophic for- getting in neural networks.Proceedings of the national academy of sciences, 114(13):3521–3526, 2017

    work page 2017

  19. [19]

    Parallel tracking and mapping for small ar workspaces

    Georg Klein and David Murray. Parallel tracking and mapping for small ar workspaces. In2007 6th IEEE and ACM international symposium on mixed and augmented reality, pages 225–234. IEEE, 2007

    work page 2007

  20. [20]

    Barf: Bundle-adjusting neural radiance fields

    Chen-Hsuan Lin, Wei-Chiu Ma, Antonio Torralba, and Simon Lucey. Barf: Bundle-adjusting neural radiance fields. InProceedings of the IEEE/CVF international conference on computer vision, pages 5741–5751, 2021

    work page 2021

  21. [21]

    Gradient episodic memory for continual learning.Advances in neural information processing systems, 30, 2017

    David Lopez-Paz and Marc’Aurelio Ranzato. Gradient episodic memory for continual learning.Advances in neural information processing systems, 30, 2017

    work page 2017

  22. [22]

    Packnet: Adding multiple tasks to a single network by iterative pruning

    Arun Mallya and Svetlana Lazebnik. Packnet: Adding multiple tasks to a single network by iterative pruning. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 7765–7773, 2018

    work page 2018

  23. [23]

    Nerf: Representing scenes as neural radiance fields for view synthesis.Communications of the ACM, 65(1):99– 106, 2021

    Ben Mildenhall, Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view synthesis.Communications of the ACM, 65(1):99– 106, 2021

    work page 2021

  24. [24]

    Neural importance sampling.ACM Trans

    Thomas M ¨uller, Brian Mcwilliams, Fabrice Rousselle, Markus Gross, and Jan Nov ´ak. Neural importance sampling.ACM Trans. Graph., 38(5), October 2019. ISSN 0730-0301. doi: 10.1145/3341156. URL https: //doi.org/10.1145/3341156

    work page doi:10.1145/3341156 2019

  25. [25]

    Instant neural graphics primitives with a multiresolution hash encoding,

    Thomas M ¨uller, Alex Evans, Christoph Schied, and Alexander Keller. Instant neural graphics primitives with a multiresolution hash encoding.ACM Trans. Graph., 41(4), July 2022. ISSN 0730-0301. doi: 10.1145/3528223.3530127. URL https://doi.org/10.1145/ 3528223.3530127

    work page doi:10.1145/3528223.3530127 2022

  26. [26]

    Distributed sub- gradient methods for multi-agent optimization.IEEE Transactions on automatic control, 54(1):48–61, 2009

    Angelia Nedic and Asuman Ozdaglar. Distributed sub- gradient methods for multi-agent optimization.IEEE Transactions on automatic control, 54(1):48–61, 2009

    work page 2009

  27. [27]

    In: 2011 10th IEEE International Symposium on Mixed and Augmented Reality, pp

    Richard A. Newcombe, Shahram Izadi, Otmar Hilliges, David Molyneaux, David Kim, Andrew J. Davison, Push- meet Kohi, Jamie Shotton, Steve Hodges, and Andrew Fitzgibbon. Kinectfusion: Real-time dense surface map- ping and tracking. In2011 10th IEEE International Symposium on Mixed and Augmented Reality, pages 127– 136, 2011. doi: 10.1109/ISMAR.2011.6092378

    work page doi:10.1109/ismar.2011.6092378 2011

  28. [28]

    Real-time 3d reconstruction at scale using voxel hashing.ACM Transactions on Graphics (ToG), 32(6):1–11, 2013

    Matthias Nießner, Michael Zollh ¨ofer, Shahram Izadi, and Marc Stamminger. Real-time 3d reconstruction at scale using voxel hashing.ACM Transactions on Graphics (ToG), 32(6):1–11, 2013

    work page 2013

  29. [29]

    Continual lifelong learning with neural networks: A review.Neural net- works, 113:54–71, 2019

    German I Parisi, Ronald Kemker, Jose L Part, Christo- pher Kanan, and Stefan Wermter. Continual lifelong learning with neural networks: A review.Neural net- works, 113:54–71, 2019

    work page 2019

  30. [30]

    Habitat 3.0: A co-habitat for humans, avatars and robots, 2023

    Xavi Puig, Eric Undersander, Andrew Szot, Mikael Dal- laire Cote, Ruslan Partsey, Jimmy Yang, Ruta Desai, Alexander William Clegg, Michal Hlavac, Tiffany Min, Theo Gervet, Vladim ´ır V ondruˇs, Vincent-Pierre Berges, John Turner, Oleksandr Maksymets, Zsolt Kira, Mrinal Kalakrishnan, Jitendra Malik, Devendra Singh Chaplot, Unnat Jain, Dhruv Batra, Akshara ...

    work page 2023

  31. [31]

    Encoder based lifelong learning

    Amal Rannen, Rahaf Aljundi, Matthew B Blaschko, and Tinne Tuytelaars. Encoder based lifelong learning. In Proceedings of the IEEE international conference on computer vision, pages 1320–1328, 2017

    work page 2017

  32. [32]

    icarl: Incremental classifier and representation learning

    Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, and Christoph H Lampert. icarl: Incremental classifier and representation learning. InProceedings of the IEEE conference on Computer Vision and Pattern Recognition, pages 2001–2010, 2017

    work page 2001

  33. [33]

    Catastrophic forgetting, rehearsal and pseudorehearsal.Connection Science, 7(2):123–146, 1995

    Anthony Robins. Catastrophic forgetting, rehearsal and pseudorehearsal.Connection Science, 7(2):123–146, 1995

    work page 1995

  34. [34]

    Experience replay for continual learning.Advances in neural information processing systems, 32, 2019

    David Rolnick, Arun Ahuja, Jonathan Schwarz, Timothy Lillicrap, and Gregory Wayne. Experience replay for continual learning.Advances in neural information processing systems, 32, 2019

    work page 2019

  35. [35]

    Habitat: A Platform for Embodied AI Research

    Manolis Savva, Abhishek Kadian, Oleksandr Maksymets, Yili Zhao, Erik Wijmans, Bhavana Jain, Julian Straub, Jia Liu, Vladlen Koltun, Jitendra Malik, Devi Parikh, and Dhruv Batra. Habitat: A Platform for Embodied AI Research. InProceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2019

    work page 2019

  36. [36]

    Stochastic neural radiance fields: Quantifying uncertainty in implicit 3d represen- tations

    Jianxiong Shen, Adria Ruiz, Antonio Agudo, and Francesc Moreno-Noguer. Stochastic neural radiance fields: Quantifying uncertainty in implicit 3d represen- tations. In2021 International Conference on 3D Vision (3DV), pages 972–981. IEEE, 2021

    work page 2021

  37. [37]

    On the linear convergence of the admm in de- centralized consensus optimization.IEEE Transactions on Signal Processing, 62(7):1750–1761, 2014

    Wei Shi, Qing Ling, Kun Yuan, Gang Wu, and Wotao Yin. On the linear convergence of the admm in de- centralized consensus optimization.IEEE Transactions on Signal Processing, 62(7):1750–1761, 2014. doi: 10.1109/TSP.2014.2304432

    work page doi:10.1109/tsp.2014.2304432 2014

  38. [38]

    Continual learning with deep generative replay

    Hanul Shin, Jung Kwon Lee, Jaehong Kim, and Jiwon Kim. Continual learning with deep generative replay. Advances in neural information processing systems, 30, 2017

    work page 2017

  39. [39]

    Distributed optimization and statistical learning via the alternating direction method of multipliers,

    Boyd Stephen, Parikh Neal, Chu Eric, Peleato Borja, and Eckstein Jonathan. Distributed optimization and statistical learning via the alternating direction method of multipliers.Foundations and Trends in Informa- tion Retrieval, 3(1):1–122, 07 2011. ISSN 1554-0669. doi: 10.1561/2200000016. URL https://doi.org/10.1561/ 2200000016

    work page doi:10.1561/2200000016 2011

  40. [40]

    Julian Straub, Thomas Whelan, Lingni Ma, Yufan Chen, Erik Wijmans, Simon Green, Jakob J. Engel, Raul Mur-Artal, Carl Ren, Shobhit Verma, Anton Clarkson, Mingfei Yan, Brian Budge, Yajie Yan, Xiaqing Pan, June Yon, Yuyang Zou, Kimberly Leon, Nigel Carter, Jesus Briales, Tyler Gillingham, Elias Mueggler, Luis Pesqueira, Manolis Savva, Dhruv Batra, Hauke M. S...

    work page internal anchor Pith review Pith/arXiv arXiv 1906

  41. [41]

    imap: Implicit mapping and positioning in real-time

    Edgar Sucar, Shikun Liu, Joseph Ortiz, and Andrew J Davison. imap: Implicit mapping and positioning in real-time. InProceedings of the IEEE/CVF international conference on computer vision, pages 6229–6238, 2021

    work page 2021

  42. [42]

    Density-aware nerf ensembles: Quantifying predictive uncertainty in neural radiance fields.arXiv preprint arXiv:2209.08718, 2022

    Niko S ¨underhauf, Jad Abou-Chakra, and Dimity Miller. Density-aware nerf ensembles: Quantifying predictive uncertainty in neural radiance fields.arXiv preprint arXiv:2209.08718, 2022

    work page arXiv 2022

  43. [43]

    Habitat 2.0: Training home assistants to re- arrange their habitat

    Andrew Szot, Alex Clegg, Eric Undersander, Erik Wij- mans, Yili Zhao, John Turner, Noah Maestre, Mustafa Mukadam, Devendra Chaplot, Oleksandr Maksymets, Aaron Gokaslan, Vladimir V ondrus, Sameer Dharur, Franziska Meier, Wojciech Galuba, Angel Chang, Zsolt Kira, Vladlen Koltun, Jitendra Malik, Manolis Savva, and Dhruv Batra. Habitat 2.0: Training home assi...

    work page 2021

  44. [44]

    Co-slam: Joint coordinate and sparse parametric encod- ings for neural real-time slam

    Hengyi Wang, Jingwen Wang, and Lourdes Agapito. Co-slam: Joint coordinate and sparse parametric encod- ings for neural real-time slam. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 13293–13302, 2023

    work page 2023

  45. [45]

    A comprehensive survey of continual learning: Theory, method and application.IEEE transactions on pat- tern analysis and machine intelligence, 46(8):5362–5383, 2024

    Liyuan Wang, Xingxing Zhang, Hang Su, and Jun Zhu. A comprehensive survey of continual learning: Theory, method and application.IEEE transactions on pat- tern analysis and machine intelligence, 46(8):5362–5383, 2024

    work page 2024

  46. [46]

    NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction

    Peng Wang, Lingjie Liu, Yuan Liu, Christian Theobalt, Taku Komura, and Wenping Wang. Neus: Learning neural implicit surfaces by volume rendering for multi- view reconstruction.arXiv preprint arXiv:2106.10689, 2021

    work page internal anchor Pith review Pith/arXiv arXiv 2021

  47. [47]

    Elastic- fusion: Dense slam without a pose graph

    Thomas Whelan, Stefan Leutenegger, Renato F Salas- Moreno, Ben Glocker, and Andrew J Davison. Elastic- fusion: Dense slam without a pose graph. InRobotics: science and systems, volume 11. Rome, 2015

    work page 2015

  48. [48]

    Zamir, Zhi-Yang He, Alexander Sax, Jitendra Malik, and Silvio Savarese

    Fei Xia, Amir R. Zamir, Zhi-Yang He, Alexander Sax, Jitendra Malik, and Silvio Savarese. Gibson Env: real- world perception for embodied agents. InComputer Vision and Pattern Recognition (CVPR), 2018 IEEE Conference on. IEEE, 2018

    work page 2018

  49. [49]

    Reinforced continual learning

    Ju Xu and Zhanxing Zhu. Reinforced continual learning. Advances in neural information processing systems, 31, 2018

    work page 2018

  50. [50]

    Continual neural mapping: Learning an implicit scene representation from sequential observations

    Zike Yan, Yuxin Tian, Xuesong Shi, Ping Guo, Peng Wang, and Hongbin Zha. Continual neural mapping: Learning an implicit scene representation from sequential observations. InProceedings of the IEEE/CVF Inter- national Conference on Computer Vision, pages 15782– 15792, 2021

    work page 2021

  51. [51]

    Active neural mapping

    Zike Yan, Haoxiang Yang, and Hongbin Zha. Active neural mapping. InProceedings of the IEEE/CVF Inter- national Conference on Computer Vision (ICCV), pages 10981–10992, October 2023

    work page 2023

  52. [52]

    V olume rendering of neural implicit surfaces.Advances in neural information processing systems, 34:4805–4815, 2021

    Lior Yariv, Jiatao Gu, Yoni Kasten, and Yaron Lipman. V olume rendering of neural implicit surfaces.Advances in neural information processing systems, 34:4805–4815, 2021

    work page 2021

  53. [53]

    Dinno: Distributed neural network optimization for multi-robot collaborative learning.IEEE Robotics and Automation Letters, 7(2):1896–1903, 2022

    Javier Yu, Joseph A Vincent, and Mac Schwager. Dinno: Distributed neural network optimization for multi-robot collaborative learning.IEEE Robotics and Automation Letters, 7(2):1896–1903, 2022

    work page 1903

  54. [54]

    Monosdf: Exploring monoc- ular geometric cues for neural implicit surface recon- struction.Advances in neural information processing systems, 35:25018–25032, 2022

    Zehao Yu, Songyou Peng, Michael Niemeyer, Torsten Sattler, and Andreas Geiger. Monosdf: Exploring monoc- ular geometric cues for neural implicit surface recon- struction.Advances in neural information processing systems, 35:25018–25032, 2022

    work page 2022

  55. [55]

    Ramen: Real-time asynchronous multi-agent neural implicit map- ping.arXiv preprint arXiv:2502.19592, 2025

    Hongrui Zhao, Boris Ivanovic, and Negar Mehr. Ramen: Real-time asynchronous multi-agent neural implicit map- ping.arXiv preprint arXiv:2502.19592, 2025

    work page arXiv 2025

  56. [56]

    Udon: Uncertainty-weighted distributed op- timization for multi-robot neural implicit mapping un- der extreme communication constraints.arXiv preprint arXiv:2509.12702, 2025

    Hongrui Zhao, Xunlan Zhou, Boris Ivanovic, and Ne- gar Mehr. Udon: Uncertainty-weighted distributed op- timization for multi-robot neural implicit mapping un- der extreme communication constraints.arXiv preprint arXiv:2509.12702, 2025

    work page arXiv 2025

  57. [57]

    Static-dynamic co-teaching for class-incremental 3d object detection

    Na Zhao and Gim Hee Lee. Static-dynamic co-teaching for class-incremental 3d object detection. InProceed- ings of the AAAI Conference on Artificial Intelligence, volume 36, pages 3436–3445, 2022

    work page 2022

  58. [58]

    Nice-slam: Neural implicit scalable encoding for slam

    Zihan Zhu, Songyou Peng, Viktor Larsson, Weiwei Xu, Hujun Bao, Zhaopeng Cui, Martin R Oswald, and Marc Pollefeys. Nice-slam: Neural implicit scalable encoding for slam. InProceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12786– 12796, 2022. APPENDIX A. Quantitative Metrics for Geometry Evaluation To assess the accura...

    work page 2022