Pith. sign in

REVIEW 1 cited by

Inverse Neural Rendering for Explainable Multi-Object Tracking

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.12359 v1 pith:WC77Y7TV submitted 2024-04-18 cs.CV cs.GRcs.RO

classification cs.CVcs.GRcs.RO
keywords trackingdatasetsimagemethodnetworksrenderingfine-tuninggenerative
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Today, most methods for image understanding tasks rely on feed-forward neural networks. While this approach has allowed for empirical accuracy, efficiency, and task adaptation via fine-tuning, it also comes with fundamental disadvantages. Existing networks often struggle to generalize across different datasets, even on the same task. By design, these networks ultimately reason about high-dimensional scene features, which are challenging to analyze. This is true especially when attempting to predict 3D information based on 2D images. We propose to recast 3D multi-object tracking from RGB cameras as an \emph{Inverse Rendering (IR)} problem, by optimizing via a differentiable rendering pipeline over the latent space of pre-trained 3D object representations and retrieve the latents that best represent object instances in a given input image. To this end, we optimize an image loss over generative latent spaces that inherently disentangle shape and appearance properties. We investigate not only an alternate take on tracking but our method also enables examining the generated objects, reasoning about failure situations, and resolving ambiguous cases. We validate the generalization and scaling capabilities of our method by learning the generative prior exclusively from synthetic data and assessing camera-based 3D tracking on the nuScenes and Waymo datasets. Both these datasets are completely unseen to our method and do not require fine-tuning. Videos and code are available at https://light.princeton.edu/inverse-rendering-tracking/.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. DNF-Intrinsic: Deterministic Noise-Free Diffusion for Indoor Inverse Rendering

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A diffusion model fine-tuned with flow matching maps a single RGB indoor image directly to five scene properties, beating prior inverse rendering methods on InteriorVerse and real-world benchmarks.

Pith tools