activity
20242026
collaborators

7 papers

cs.LG2026

Remember to be Curious: Episodic Context and Persistent Worlds for 3D Exploration

Lily Goli, Justin Kerr, Daniele Reda +3

Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon tasks, particularly within 3D environments. Curiosity-driven reinforcement learning addre…

cs.CV2026

Flux4D: Flow-based Unsupervised 4D Reconstruction

Jingkang Wang, Henry Che, Yun Chen +4

Reconstructing large-scale dynamic scenes from visual observations is a fundamental challenge in computer vision, with critical implications for robotics and autonomous systems. Wh…

cs.CV2026

FullCircle: Effortless 3D Reconstruction from Casual 360 Captures

Yalda Foroutan, Ipek Oztas, Daniel Rebain +4

Radiance fields have emerged as powerful tools for 3D scene reconstruction. However, casual capture remains challenging due to the narrow field of view of perspective cameras, whic…

cs.CV2026

Grow with the Flow: 4D Reconstruction of Growing Plants with Gaussian Flow Fields

Weihan Luo, Lily Goli, Sherwin Bahmani +3

Modeling the time-varying 3D appearance of plants during growth poses unique challenges: unlike most dynamic scenes, plants continuously generate new geometry as they expand, branc…

cs.CV2026

Hierarchical Transformers for Unsupervised 3D Shape Abstraction

Aditya Vora, Lily Goli, Andrea Tagliasacchi +1

We introduce HiT, a novel hierarchical neural field representation for 3D shapes that learns general hierarchies in a coarse-to-fine manner across different shape categories in an…

cs.CV2025

3D Gaussian Flats: Hybrid 2D/3D Photometric Scene Reconstruction

Maria Taktasheva, Lily Goli, Alessandro Fiorini +3

Recent advances in radiance fields and novel view synthesis enable creation of realistic digital twins from photographs. However, current methods struggle with flat, texture-less s…