Seeing a Rose in Five Thousand Ways
What is a rose, visually? A rose comprises its intrinsics, including the distribution of geometry, texture, and material specific to its object category. With knowledge of these intrinsic properties, we may render roses of different sizes and shapes, in different poses, and under different lighting conditions. In this work, we build a generative model that learns to capture such object intrinsics from a single image, such as a photo of a bouquet. Such an image includes multiple instances of an object type. These instances all share the same intrinsics, but appear different due to a combination of variance within these intrinsics and differences in extrinsic factors, such as pose and illumination. Experiments show that our model successfully learns object intrinsics (distribution of geometry, texture, and material) for a wide range of objects, each from a single Internet image. Our method achieves superior results on multiple downstream tasks, including intrinsic image decomposition, shape and image generation, view synthesis, and relighting.
Code (1)
Tasks
Image GenerationIntrinsic Image DecompositionObjectSimilar Papers 제목 키워드 기반
Seeing Faces in Things: A Model and Dataset for Pareidolia
The human visual system is well-tuned to detect faces of all shapes and sizes. While this brings obvious survival advantages, such as a better chance of spotting unknown predators in the bush, it also leads to spurious f…
Search for developments of a box having multiple ways of folding by SAT solver
A polyomino is called a development if it can make a box by folding edges of unit squares forming the polyomino. It is known that there are developments that can fold into a box (or boxes) in multiple ways. In this work,…
Challenges in Finding Metaphorical Connections
Poetry is known for its novel expression using figurative language. We introduce a writing task that contains the essential challenges of generating meaningful figurative language and can be evaluated. We investigate how…
Global analysis of a predator-prey model with variable predator search rate
We consider a modified Rosenzweig-MacArthur predator-prey model, based on the premise that the search rate of predators is dependent on the prey density, rather than constant. A complete analysis of the global behavior o…
RosettaSpeech: Zero-Shot Speech-to-Speech Translation without Parallel Speech
End-to-end speech-to-speech translation (S2ST) systems typically struggle with a critical data bottleneck: the scarcity of parallel speech-to-speech corpora. To overcome this, we introduce RosettaSpeech, a novel zero-sho…
Speech-to-Speech TranslationMachine Translation