68 citations · 117 across the 26 of their papers we have counts for
8 papers · 1 filter
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…
StyleGAN knows Normal, Depth, Albedo, and More
Anand Bhattad, Daniel McKee, Derek Hoiem +1
Intrinsic images, in the original sense, are image-like maps of scene properties like depth, normal, albedo or shading. This paper demonstrates that StyleGAN can easily be induced…
Make It So: Steering StyleGAN for Any Image Inversion and Editing
Anand Bhattad, Viraj Shah, Derek Hoiem +1
StyleGAN's disentangled style representation enables powerful image editing by manipulating the latent variables, but accurately mapping real-world images to their latent variables…