activity
20232025
most citedTowards Scenario-based Safety Validation for Autonomous Trains with Deep Generative Models

6 citations · 6 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV2025

ReDepth Anything: Test-Time Depth Refinement via Self-Supervised Re-lighting

Ananta R. Bhattarai, Helge Rhodin

Monocular depth estimation remains challenging, as foundation models such as Depth Anything V2 (DA-V2) struggle with real-world images that are far from the training distribution.…

cs.CV2025

Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks

Dmitrii Pozdeev, Alexey Artemov, Ananta R. Bhattarai +1

We propose DenseMarks - a new learned representation for human heads, enabling high-quality dense correspondences of human head images. For a 2D image of a human head, a Vision Tra…

cs.CV2025

DreamTexture: Shape from Virtual Texture with Analysis by Augmentation

Ananta R. Bhattarai, Xingzhe He, Alla Sheffer +1

DreamFusion established a new paradigm for unsupervised 3D reconstruction from virtual views by combining advances in generative models and differentiable rendering. However, the u…

cs.LG2024

Provably Better Explanations with Optimized Aggregation of Feature Attributions

Thomas Decker, Ananta R. Bhattarai, Jindong Gu +2

Using feature attributions for post-hoc explanations is a common practice to understand and verify the predictions of opaque machine learning models. Despite the numerous technique…

cs.LG20236 cited

Towards Scenario-based Safety Validation for Autonomous Trains with Deep Generative Models

Thomas Decker, Ananta R. Bhattarai, Michael Lebacher

Modern AI techniques open up ever-increasing possibilities for autonomous vehicles, but how to appropriately verify the reliability of such systems remains unclear. A common approa…