Papers › Zero-Shot Text-Guided Object Generation with Dream Fields

Zero-Shot Text-Guided Object Generation with Dream Fields

2 Dec 2021CVPR 2022 1arXiv:2112.01455archive 2025-07-28

Ajay Jain, Ben Mildenhall, Jonathan T. Barron, Pieter Abbeel, Ben Poole

We combine neural rendering with multi-modal image and text representations to synthesize diverse 3D objects solely from natural language descriptions. Our method, Dream Fields, can generate the geometry and color of a wide range of objects without 3D supervision. Due to the scarcity of diverse, captioned 3D data, prior methods only generate objects from a handful of categories, such as ShapeNet. Instead, we guide generation with image-text models pre-trained on large datasets of captioned images from the web. Our method optimizes a Neural Radiance Field from many camera views so that rendered images score highly with a target caption according to a pre-trained CLIP model. To improve fidelity and visual quality, we introduce simple geometric priors, including sparsity-inducing transmittance regularization, scene bounds, and new MLP architectures. In experiments, Dream Fields produce realistic, multi-view consistent object geometry and color from a variety of natural language captions.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2112.01455")

Code

Syntology Ran 1 of 10 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: community (archive-listed): 10 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ashawkey/torch-ngp mentioned on GitHubpytorch report
autodeskailab/clip-forge mentioned on GitHubpytorch report
shengyu-meng/dreamfields-3D mentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

10 samples harvested; 1 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
9unverified

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from shengyu-meng/dreamfields-3D. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

sample_pdf shengyu-meng/dreamfields-3D/nerf/renderer.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 8ed7b9fc7f33d1dd · report
constrain_l_inf shengyu-meng/dreamfields-3D/nerf/bg_utils.py community (archive-listed) unverified MIT (permissive) · 10b170fee86dc30d · report
get_encoder shengyu-meng/dreamfields-3D/encoding.py community (archive-listed) unverified MIT (permissive) · 72d37c800336a0ba · report
get_view_direction shengyu-meng/dreamfields-3D/nerf/provider.py community (archive-listed) unverified MIT (permissive) · 08f9890fc9f0a74b · report
mape_loss shengyu-meng/dreamfields-3D/loss.py community (archive-listed) unverified MIT (permissive) · c6a72f3eb1bcaedc · report
near_far_from_bound shengyu-meng/dreamfields-3D/nerf/renderer.py community (archive-listed) unverified MIT (permissive) · 58cb35f56b5a61a5 · report
nerf_matrix_to_ngp shengyu-meng/dreamfields-3D/nerf/provider.py community (archive-listed) unverified MIT (permissive) · ea0c1ea3b1314a9f · report
rand_poses shengyu-meng/dreamfields-3D/nerf/provider.py community (archive-listed) unverified MIT (permissive) · 6a0981461a74375d · report
rfft2d_freqs shengyu-meng/dreamfields-3D/nerf/bg_utils.py community (archive-listed) unverified MIT (permissive) · 66f0c9fbbdec320b · report
to_valid_rgb shengyu-meng/dreamfields-3D/nerf/bg_utils.py community (archive-listed) unverified MIT (permissive) · 0d8871eb5635a546 · report

Tasks

Neural RenderingObject

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CLIP

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections