publications

We introduce RealmDreamer, a technique for generation of general forward-facing 3D scenes from text descriptions. Our technique optimizes a 3D Gaussian Splatting representation to match complex text prompts. We initialize these splats by utilizing the state-of-the-art text-to-image generators, lifting their samples into 3D, and computing the occlusion volume. We then optimize this representation across multiple views as a 3D inpainting task with image-conditional diffusion models. To learn correct geometric structure, we incorporate a depth diffusion model by conditioning on the samples from the inpainting model, giving rich geometric structure. Finally, we finetune the model using sharpened samples from image generators. Notably, our technique does not require training on any scene-specific dataset and can synthesize a variety of high-quality 3D scenes in different styles, consisting of multiple objects. Its generality additionally allows 3D synthesis from a single image.

Research papers are a vital building block for scientific discussion. While these papers follow effective structures for the relevant community, they are unable to cater to novice readers and express otherwise creative ideas in creative mediums. To this end, we propose ZINify, the first approach to automatically transform research papers into engaging zines using large language models (LLM) and text-to-image generators. Following zine’s long history of supporting independent, creative expression, we propose a technique that can work with authors to build more engaging, marketable, and unconventional content that is based on their research. We believe that our work will help make research more engaging and accessible to all while helping papers stand out in crowded online venues.

Reading, much like music listening, is an immersive experience that transports readers while taking them on an emotional journey. Listening to complementary music has the potential to amplify the reading experience, especially when the music is stylistically cohesive and emotionally relevant. In this paper, we propose the first fully automatic method to build a dense soundtrack for books, which can play high-quality instrumental music for the entirety of the reading duration. Our work employs a unique text processing and music weaving pipeline that determines the context and emotional composition of scenes in a chapter. This allows our method to identify and play relevant excerpts from the soundtrack of the book’s movie adaptation. By relying on the movie composer’s craftsmanship, our book soundtracks include expert-made motifs and other scene-specific musical characteristics. We validate the design decisions of our approach through a perceptual study. Our readers note that the book soundtrack greatly enhanced their reading experience, due to high immersiveness granted via uninterrupted and style-consistent music, and a heightened emotional state attained via high precision emotion and scene context recognition.

In this work, we propose IndoLayout, a novel realtime approach for generating high-quality occupancy maps from an RGB image for indoor scenes. Such occupancy maps are often crucial for path-planning and mapping in indoor environments but are often built using only information contained in the ego view. In contrast, our approach also predicts occupancy values beyond immediately visible regions from just a monocular image, leveraging learnt priors from indoor scenes. Hence, our proposed network can produce a hallucinated, amodal scene layout that includes areas occluded in the RGB image, such as a navigable floor behind a desk. Specifically, we propose a novel architecture that uses self-attention and adversarial learning to vastly improve the quality of the predicted layout. We evaluate our model on several photorealistic indoor datasets and outperform previous relevant work on all metrics that measure layout quality, including newly adopted ones. Finally, we demonstrate the effectiveness of our method by showing significant improvements on the PointNav task over similar approaches using IndoLayout.

Music affects and in some cases reflects one’s emotional state. Key to this influence is lyrics and their meaning in conjunction with the acoustic properties of the track. Recent work has focused on analysing these acoustic properties and showing that individuals prone to depression primarily consume low valence and low energy music. However, no studies yet have explored lyrical content preferences in relation to online music consumption of such individuals. In the current study, we examine lyrical simplicity, measured as the Compressibility and Ab- solute Information Content of the text, associated with preferences of individuals at risk for depression. Using the six-month listening history of 541 Last.fm users, we compare lyrical simplicity trends for users grouped as being at risk (At-Risk) of de- pression from those that are not (No-Risk). Our findings reveal that At-Risk individuals prefer songs with greater information content (lower Compressibility) on average, especially for songs characterised as Sad. Furthermore, we found that At-Risk individuals also have greater variability of Absolute Information Content across their listening history. We discuss the results in light of existing socio-psychological lab-based research on music habits associated with depression and their relevance to naturally occurring online music listening behaviour.