4 papers · 1 filter
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…
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…
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…
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…