68 citations · 117 across the 26 of their papers we have counts for
35 papers
OmniRay: Camera-Agnostic Monocular 3D Reconstruction with Composite Ray Fields
Namitha Guruprasad, Abhay Yadav, Cheng Peng +2
Monocular models recover 3D geometry from a single image in one pass, but most assume a pinhole camera and produce distorted geometry on the wide-angle imagery produced by fisheye…
Generative Cinematographer: Composing Camera and Object Motion in 3D
Jiahan Zhang, Chaohao Yang, Namitha Guruprasad +4
Current controllable video generation systems often rely on 2D motion trajectories or sparse drag signals for object motion. These controls are ambiguous because the same 2D trajec…
PowerSim: Differentiable Physics Simulation and Rendering with Power Diagrams
Trong-Tung Nguyen, Anand Bhattad
We introduce PowerSim, a method to bring physically grounded, differentiable dynamics to PowerFoam's power diagram based 3D representation. PowerSim directly couples a pre-trained…
FracGen: Learning How Objects Stretch and Tear with Physics-Informed Video Generation
Trong-Tung Nguyen, Jiahan Zhang, Anand Bhattad
We introduce FracGen, a fracture-aware video generation model that produces plausible, controllable fracture dynamics from a single image of an intact object, conditioned on physic…
Thinking in Boxes: 3D Editing in Real Images Made Easy
Pradhaan S Bhat, Naveen Chandra R, Rishubh Parihar +4
Text and 2D-conditioning interfaces provide weak, ambiguous control over spatial transformations in image editing -- particularly under large object motions and camera changes. Pri…
RATS! Patches Talk Through Registers: Emergent Parts in Register Attention Transformers
Timing Yang, Predrag Neskovic, Jansen Seheult +4
When humans see a bird, they recognize far more than just "bird" -- they see a head, wings, and talons, a structured assembly of reusable parts that can be identified across every…
Generalizable Sparse-View 3D Reconstruction from Unconstrained Images
Vinayak Gupta, Chih-Hao Lin, Shenlong Wang +2
Reconstructing 3D scenes from sparse, unposed images remains challenging under real-world conditions with varying illumination and transient occlusions. Existing methods rely on sc…
SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization
Deming Li, Abhay Yadav, Cheng Peng +2
We present SyncFix, a framework that enforces cross-view consistency during the diffusion-based refinement of reconstructed scenes. SyncFix formulates refinement as a joint latent…
SyncLight: Single-Edit Multi-View Relighting
David Serrano-Lozano, Anand Bhattad, Luis Herranz +2
We present SyncLight, a method to enable consistent, parametric control over light sources across multiple uncalibrated views of a static scene conditioned on a single view. While…
Generative Blocks World: Moving Things Around in Pictures
Vaibhav Vavilala, Seemandhar Jain, Rahul Vasanth +2
We describe Generative Blocks World to interact with the scene of a generated image by manipulating simple geometric abstractions. Our method represents scenes as assemblies of con…
Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting
Anand Bhattad, Konpat Preechakul, Alexei A. Efros
This paper proposes a novel scene understanding task called Visual Jenga. Drawing inspiration from the game Jenga, the proposed task involves progressively removing objects from a…
From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos
Matthew Wallingford, Anand Bhattad, Aditya Kusupati +7
Three-dimensional (3D) understanding of objects and scenes play a key role in humans' ability to interact with the world and has been an active area of research in computer vision,…
LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting
Xiaoyan Xing, Konrad Groh, Sezer Karaoglu +2
We introduce LumiNet, a novel architecture that leverages generative models and latent intrinsic representations for effective lighting transfer. Given a source image and a target…
ScribbleLight: Single Image Indoor Relighting with Scribbles
Jun Myeong Choi, Annie Wang, Pieter Peers +2
Image-based relighting of indoor rooms creates an immersive virtual understanding of the space, which is useful for interior design, virtual staging, and real estate. Relighting in…
ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion
Zitian Zhang, Frédéric Fortier-Chouinard, Mathieu Garon +2
We present ZeroComp, an effective zero-shot 3D object compositing approach that does not require paired composite-scene images during training. Our method leverages ControlNet to c…
Latent Intrinsics Emerge from Training to Relight
Xiao Zhang, William Gao, Seemandhar Jain +3
Image relighting is the task of showing what a scene from a source image would look like if illuminated differently. Inverse graphics schemes recover an explicit representation of…
Improved Convex Decomposition with Ensembling and Negative Primitives
Vaibhav Vavilala, Florian Kluger, Seemandhar Jain +3
Describing a scene in terms of primitives -- geometrically simple shapes that offer a parsimonious but accurate abstraction of structure -- is an established and difficult fitting…
Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion
Xiang Fan, Anand Bhattad, Ranjay Krishna
We introduce Videoshop, a training-free video editing algorithm for localized semantic edits. Videoshop allows users to use any editing software, including Photoshop and generative…
Shadows Don't Lie and Lines Can't Bend! Generative Models don't know Projective Geometry...for now
Ayush Sarkar, Hanlin Mai, Amitabh Mahapatra +3
Generative models can produce impressively realistic images. This paper demonstrates that generated images have geometric features different from those of real images. We build a s…
Generative Models: What Do They Know? Do They Know Things? Let's Find Out!
Xiaodan Du, Nicholas Kolkin, Greg Shakhnarovich +1
Generative models excel at mimicking real scenes, suggesting they might inherently encode important intrinsic scene properties. In this paper, we aim to explore the following key q…
Improving Equivariance in State-of-the-Art Supervised Depth and Normal Predictors
Yuanyi Zhong, Anand Bhattad, Yu-Xiong Wang +1
Dense depth and surface normal predictors should possess the equivariant property to cropping-and-resizing -- cropping the input image should result in cropping the same output ima…
OBJECT 3DIT: Language-guided 3D-aware Image Editing
Oscar Michel, Anand Bhattad, Eli VanderBilt +3
Existing image editing tools, while powerful, typically disregard the underlying 3D geometry from which the image is projected. As a result, edits made using these tools may become…
Blocks2World: Controlling Realistic Scenes with Editable Primitives
Vaibhav Vavilala, Seemandhar Jain, Rahul Vasanth +2
We present Blocks2World, a novel method for 3D scene rendering and editing that leverages a two-step process: convex decomposition of images and conditioned synthesis. Our techniqu…
UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video
Chih-Hao Lin, Bohan Liu, Yi-Ting Chen +5
We present UrbanIR (Urban Scene Inverse Rendering), a new inverse graphics model that enables realistic, free-viewpoint renderings of scenes under various lighting conditions with…