1 citations · 1 across the 13 of their papers we have counts for
13 papers
Auteur: Language-Driven Cinematographic Framing for Human-Centric Video Generation
Muhammed Burak Kizil, Enes Sanli, Niloy J. Mitra +4
Generative video models have achieved remarkable visual fidelity and temporal coherence, yet intentional camera control remains elusive. Existing frameworks treat camera motion as…
ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes
Honglin Chen, Karran Pandey, Rundi Wu +6
Kinematic rigs provide a structured interface for articulating 3D meshes but lack any associated pose space, i.e., an explicit representation of the plausible manifold of joint con…
LoST: Level of Semantics Tokenization for 3D Shapes
Niladri Shekhar Dutt, Zifan Shi, Paul Guerrero +4
Tokenization is a fundamental technique in the generative modeling of various modalities. In particular, it plays a critical role in autoregressive (AR) models, which have recently…
A Mixed Diet Makes DINO An Omnivorous Vision Encoder
Rishabh Kabra, Maks Ovsjanikov, Drew A. Hudson +5
Pre-trained vision encoders like DINOv2 have demonstrated exceptional performance on unimodal tasks. However, we observe that their features are poorly aligned across different vis…
LAMP: Language-Assisted Motion Planning for Controllable Video Generation
Muhammed Burak Kizil, Enes Sanli, Niloy J. Mitra +3
Video generation has achieved remarkable progress in visual fidelity and controllability, enabling conditioning on text, layout, or motion. Among these, motion control - specifying…
MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills
Niladri Shekhar Dutt, Duygu Ceylan, Niloy J. Mitra
Retouching is an essential task in post-manipulation of raw photographs. Generative editing, guided by text or strokes, provides a new tool accessible to users but can easily chang…
ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models
R. Kenny Jones, Paul Guerrero, Niloy J. Mitra +1
We present ShapeLib, the first method that uses the priors of Large Language Models (LLMs) to design libraries of programmatic 3D shape abstractions. Our system accepts two forms o…
JOG3R: Towards 3D-Consistent Video Generators
Chun-Hao Paul Huang, Niloy Mitra, Hyeonho Jeong +2
Emergent capabilities of image generators have led to many impactful zero- or few-shot applications. Inspired by this success, we investigate whether video generators similarly exh…
GANFusion: Feed-Forward Text-to-3D with Diffusion in GAN Space
Souhaib Attaiki, Paul Guerrero, Duygu Ceylan +2
We train a feed-forward text-to-3D diffusion generator for human characters using only single-view 2D data for supervision. Existing 3D generative models cannot yet match the fidel…
Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation
Hyeonho Jeong, Chun-Hao Paul Huang, Jong Chul Ye +2
While recent foundational video generators produce visually rich output, they still struggle with appearance drift, where objects gradually degrade or change inconsistently across…
Motion Modes: What Could Happen Next?
Karran Pandey, Matheus Gadelha, Yannick Hold-Geoffroy +3
Predicting diverse object motions from a single static image remains challenging, as current video generation models often entangle object movement with camera motion and other sce…
SuperGaussian: Repurposing Video Models for 3D Super Resolution
Yuan Shen, Duygu Ceylan, Paul Guerrero +4
We present a simple, modular, and generic method that upsamples coarse 3D models by adding geometric and appearance details. While generative 3D models now exist, they do not yet m…
Diffusion Handles: Enabling 3D Edits for Diffusion Models by Lifting Activations to 3D
Karran Pandey, Paul Guerrero, Matheus Gadelha +3
Diffusion Handles is a novel approach to enabling 3D object edits on diffusion images. We accomplish these edits using existing pre-trained diffusion models, and 2D image depth est…